计算机视觉论文-2021-06-15

本专栏是计算机视觉方向论文收集积累，时间：2021年6月15日，来源：paper digest

欢迎关注原创公众号 【计算机视觉联盟】，回复 【西瓜书手推笔记】 可获取我的机器学习纯手推笔记！

直达笔记地址：机器学习手推笔记（GitHub地址）

1, TITLE: Using Convolutional Neural Networks for The Helicity Classification of Magnetic Fields
AUTHORS: Nicol� Oreste Pinciroli Vago ; Ibrahim A. Hameed ; Michael Kachelriess
CATEGORY: astro-ph.HE [astro-ph.HE, cs.AI, cs.CV, cs.LG, hep-ph]
HIGHLIGHT: We propose to apply deep learning to helicity classification employing Convolutional Neural Networks and show that this method outperforms the $Q$ estimator.

2, TITLE: Entropy-based Logic Explanations of Neural Networks
AUTHORS: PIETRO BARBIERO et. al.
CATEGORY: cs.AI [cs.AI, cs.CV, cs.LG, cs.LO]
HIGHLIGHT: In this paper, we propose a novel end-to-end differentiable approach enabling the extraction of logic explanations from neural networks using the formalism of First-Order Logic.

3, TITLE: Domain Generalization on Medical Imaging Classification Using Episodic Training with Task Augmentation
AUTHORS: CHENXIN LI et. al.
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: In this paper, we propose a novel DG scheme of episodic training with task augmentation on medical imaging classification.

4, TITLE: TimeLens: Event-based Video Frame Interpolation
AUTHORS: STEPAN TULYAKOV et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work, we introduce Time Lens, a novel indicates equal contribution method that leverages the advantages of both. Finally, we release a new large-scale dataset in highly dynamic scenarios, aimed at pushing the limits of existing methods.

5, TITLE: Dynamic Clone Transformer for Efficient Convolutional Neural Netwoks
AUTHORS: Longqing Ye
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: In this paper, we introduce a novel concept termed multi-path fully connected pattern (MPFC) to rethink the interdependencies of topology pattern, accuracy and efficiency for ConvNets.

6, TITLE: Attention-based Domain Adaptation for Single Stage Detectors
AUTHORS: Vidit ; Mathieu Salzmann
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To nonetheless benefit from the strength of local adaptation, we introduce an attention mechanism that lets us identify the important regions on which adaptation should focus.

7, TITLE: Toward Automatic Interpretation of 3D Plots
AUTHORS: Laura E. Brandt ; William T. Freeman
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We approach this problem by synthesizing a new dataset of 3D grid-marked surfaces (SurfaceGrid) and training a deep neural net to estimate their shape.

8, TITLE: Hard Samples Rectification for Unsupervised Cross-domain Person Re-identification
AUTHORS: Chih-Ting Liu ; Man-Yu Lee ; Tsai-Shien Chen ; Shao-Yi Chien
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose a Hard Samples Rectification (HSR) learning scheme which resolves the weakness of original clustering-based methods being vulnerable to the hard positive and negative samples in the target unlabelled dataset.

9, TITLE: Context-Aware Image Inpainting with Learned Semantic Priors
AUTHORS: WENDONG ZHANG et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To tackle this problem, we introduce pretext tasks that are semantically meaningful to estimating the missing contents.

10, TITLE: More Real Than Real: A Study on Human Visual Perception of Synthetic Faces
AUTHORS: FEDERICA LAGO et. al.
CATEGORY: cs.CV [cs.CV, cs.CY]
HIGHLIGHT: We describe the design and results of a perceptual experiment we have conducted, where a wide and diverse group of volunteers has been exposed to synthetic face images produced by state-of-the-art Generative Adversarial Networks (namely, PG-GAN, StyleGAN, StyleGAN2).

11, TITLE: SGE Net: Video Object Detection with Squeezed GRU and Information Entropy Map
AUTHORS: Rui Su ; Wenjing Huang ; Haoyu Ma ; Xiaowei Song ; Jinglu Hu
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose an efficient method that combines channel-reduced convolutional GRU (Squeezed GRU), and Information Entropy map for video object detection (SGE-Net).

12, TITLE: Over-Fit: Noisy-Label Detection Based on The Overfitted Model Property
AUTHORS: Seulki Park ; Dae Ung Jo ; Jin Young Choi
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: In this paper, we propose a novel noisy-label detection algorithm by employing the property of overfitting on individual data points.

13, TITLE: Selection of Source Images Heavily Influences The Effectiveness of Adversarial Attacks
AUTHORS: Utku Ozbulak ; Esla Timothy Anzaku ; Wesley De Neve ; Arnout Van Messem
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: To do so, we devise a large-scale model-to-model transferability scenario for which we meticulously analyze the properties of adversarial examples, generated from every suitable source image in ImageNet by making use of two of the most frequently deployed attacks.

14, TITLE: SinIR: Efficient General Image Manipulation with Single Image Reconstruction
AUTHORS: Jihyeong Yoo ; Qifeng Chen
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We propose SinIR, an efficient reconstruction-based framework trained on a single natural image for general image manipulation, including super-resolution, editing, harmonization, paint-to-image, photo-realistic style transfer, and artistic style transfer.

15, TITLE: Discerning The Painter's Hand: Machine Learning on Surface Topography
AUTHORS: F. JI et. al.
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: This study extends machine learning analysis to surface topography of painted works.

16, TITLE: Bayesian Dense Inverse Searching Algorithm for Real-time Stereo Matching in Minimally Invasive Surgery
AUTHORS: Jingwei Song ; Qiuchen Zhu ; Jianyu Lin ; Maani Ghaffari
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We propose a Bayesian framework to evaluate the probability of the optimized patch disparity at different scales.

17, TITLE: Pay Attention with Focus: A Novel Learning Scheme for Classification of Whole Slide Images
AUTHORS: SHIVAM KALRA et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We overcome this limitation by proposing a novel two-stage approach.

18, TITLE: Mirror3D: Depth Refinement for Mirror Surfaces
AUTHORS: Jiaqi Tan ; Weijie Lin ; Angel X. Chang ; Manolis Savva
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: Our key idea is to estimate the 3D mirror plane based on RGB input and surrounding depth context, and use this estimate to directly regress mirror surface depth. To address this problem, we create the Mirror3D dataset: a 3D mirror plane dataset based on three RGBD datasets (Matterport3D, NYUv2 and ScanNet) containing 7,011 mirror instance masks and 3D planes.

19, TITLE: Automated Parking Space Detection Using Convolutional Neural Networks
AUTHORS: Julien Nyambal ; Richard Klein
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: This paper presents an approach for a real-time parking space classification based on Convolutional Neural Networks (CNN) using Caffe and Nvidia DiGITS framework.

20, TITLE: Large-Scale Unsupervised Object Discovery
AUTHORS: Huy V. Vo ; Elena Sizikova ; Cordelia Schmid ; Patrick P�rez ; Jean Ponce
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We propose a novel formulation of UOD as a ranking problem, amenable to the arsenal of distributed methods available for eigenvalue problems and link analysis.

21, TITLE: Disrupting Model Training with Adversarial Shortcuts
AUTHORS: Ivan Evtimov ; Ian Covert ; Aditya Kusupati ; Tadayoshi Kohno
CATEGORY: cs.CV [cs.CV, cs.CR, cs.LG]
HIGHLIGHT: Successful model training may be preventable with carefully designed dataset modifications, and we present a proof-of-concept approach for the image classification setting.

22, TITLE: 1st Place Solution for YouTubeVOS Challenge 2021:Video Instance Segmentation
AUTHORS: THUY C. NGUYEN et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work, we design a unified model to mutually learn these tasks.

23, TITLE: CAR-Net: Unsupervised Co-Attention Guided Registration Network for Joint Registration and Structure Learning
AUTHORS: Xiang Chen ; Yan Xia ; Nishant Ravikumar ; Alejandro F Frangi
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To better explore the correlation between the fixed and moving images and improve registration performance, we propose a novel deep learning network, Co-Attention guided Registration Network (CAR-Net).

24, TITLE: Structure-Regularized Attention for Deformable Object Representation
AUTHORS: Shenao Zhang ; Li Shen ; Zhifeng Li ; Wei Liu
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work, we consider learning representations for deformable objects which can benefit from context exploitation by modeling the structural dependencies that the data intrinsically possesses.

25, TITLE: GANs N' Roses: Stable, Controllable, Diverse Image to Image Translation (works for Videos Too!)
AUTHORS: Min Jin Chong ; David Forsyth
CATEGORY: cs.CV [cs.CV, cs.GR, cs.LG]
HIGHLIGHT: We show how to learn a map that takes a content code, derived from a face image, and a randomly chosen style code to an anime image.

26, TITLE: HR-NAS: Searching Efficient High-Resolution Neural Architectures with Lightweight Transformers
AUTHORS: MINGYU DING et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: This work proposes a novel NAS method, called HR-NAS, which is able to find efficient and accurate networks for different tasks, by effectively encoding multiscale contextual information while maintaining high-resolution representations.

27, TITLE: Partial Success in Closing The Gap Between Human and Machine Vision
AUTHORS: ROBERT GEIRHOS et. al.
CATEGORY: cs.CV [cs.CV, cs.AI, cs.LG, q-bio.NC]
HIGHLIGHT: Here we ask: Are we making progress in closing the gap between human and machine vision?

28, TITLE: HistoTransfer: Understanding Transfer Learning for Histopathology
AUTHORS: Yash Sharma ; Lubaina Ehsan ; Sana Syed ; Donald E. Brown
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work, we compare the performance of features extracted from networks trained on ImageNet and histopathology data.

29, TITLE: 3rd Place Solution for Short-video Face Parsing Challenge
AUTHORS: Xiao Liu ; XiaoFei Si ; JiangTao Xie
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We propose an Edge-Aware Network(EANet) that uses edge information to refine the segmentation edge.

30, TITLE: Unsupervised Place Recognition with Deep Embedding Learning Over Radar Videos
AUTHORS: Matthew Gadd ; Daniele De Martini ; Paul Newman
CATEGORY: cs.CV [cs.CV, cs.RO]
HIGHLIGHT: We learn, in an unsupervised way, an embedding from sequences of radar images that is suitable for solving place recognition problem using complex radar data.

31, TITLE: Go Small and Similar: A Simple Output Decay Brings Better Performance
AUTHORS: XUAN CHENG et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: By audaciously assuming there is causality involved, we propose a novel regularization term, called Output Decay, that enforces the model to assign smaller and similar output values on each class.

32, TITLE: Survey: Image Mixing and Deleting for Data Augmentation
AUTHORS: Humza Naveed
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: Due to its low compute cost and success in recent past, many techniques of image mixing and deleting are proposed.

33, TITLE: DS-TransUNet:Dual Swin Transformer U-Net for Medical Image Segmentation
AUTHORS: Ailiang Lin ; Bingzhi Chen ; Jiayu Xu ; Zheng Zhang ; Guangming Lu
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To alleviate these problems, we propose a novel deep medical image segmentation framework called Dual Swin Transformer U-Net (DS-TransUNet), which might be the first attempt to concurrently incorporate the advantages of hierarchical Swin Transformer into both encoder and decoder of the standard U-shaped architecture to enhance the semantic segmentation quality of varying medical images.

34, TITLE: A Baseline for Semi-supervised Learning of Efficient Semantic Segmentation Models
AUTHORS: Ivan Grubi?i? ; Marin Or?i? ; Sini?a ?egvi?
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: We show advantage of perturbing only the student branch and present a plausible explanation of such behaviour.

35, TITLE: 2rd Place Solutions in The HC-STVG Track of Person in Context Challenge 2021
AUTHORS: YiYu ; XinyingWang ; WeiHu ; XunLuo ; ChengLi
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this technical report, we present our solution to localize a spatio-temporal person in an untrimmed video based on a sentence.

36, TITLE: Self-training Guided Adversarial Domain Adaptation For Thermal Imagery
AUTHORS: Ibrahim Batuhan Akkaya ; Fazil Altinel ; Ugur Halici
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: In order to investigate efficacy of combining feature-rich visible spectrum and thermal image modalities, we propose an unsupervised domain adaptation method which does not require RGB-to-thermal image pairs.

37, TITLE: On-Off Center-Surround Receptive Fields for Accurate and Robust Image Classification
AUTHORS: Zahra Babaiee ; Ramin Hasani ; Mathias Lechner ; Daniela Rus ; Radu Grosu
CATEGORY: cs.CV [cs.CV, cs.AI, cs.LG, cs.NE]
HIGHLIGHT: To this end, our paper extends the receptive field of convolutional neural networks with two residual components, ubiquitous in the visual processing system of vertebrates: On-center and off-center pathways, with excitatory center and inhibitory surround; OOCS for short.

38, TITLE: Automatically Eliminating Seam Lines with Poisson Editing in Complex Relative Radiometric Normalization Mosaicking Scenarios
AUTHORS: SHIQI LIU et. al.
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: These conditions make the main feathering or blending methods, e.g., linear weighted blending and Laplacian pyramid blending, unavailable.

39, TITLE: Toward Accurate and Realistic Outfits Visualization with Attention to Details
AUTHORS: Kedan Li ; Min jin Chong ; Jeffrey Zhang ; Jingen Liu
CATEGORY: cs.CV [cs.CV, cs.GR, cs.LG]
HIGHLIGHT: Virtual try-on methods aim to generate images of fashion models wearing arbitrary combinations of garments.

40, TITLE: Dise�o Y Desarrollo De Aplicaci�n M�vil Para La Clasificaci�n De Flora Nativa Chilena Utilizando Redes Neuronales Convolucionales
AUTHORS: Ignacio Mu�oz ; Alfredo Bolt
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: This study introduces the development of a chilean species dataset and an optimized classification model implemented to a mobile app.

41, TITLE: Deception Detection and Remote Physiological Monitoring: A Dataset and Baseline Experimental Results
AUTHORS: JEREMY SPETH et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We present the Deception Detection and Physiological Monitoring (DDPM) dataset and initial baseline results on this dataset.

42, TITLE: Deterministic Guided LiDAR Depth Map Completion
AUTHORS: Bryan Krauss ; Gregory Schroeder ; Marko Gustke ; Ahmed Hussein
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: This paper presents a non-deep learning-based approach to densify a sparse LiDAR-based depth map using a guidance RGB image.

43, TITLE: DeepMMSA: A Novel Multimodal Deep Learning Method for Non-small Cell Lung Cancer Survival Analysis
AUTHORS: Yujiao Wu ; Jie Ma ; Xiaoshui Huang ; Sai Ho Ling ; Steven Weidong Su
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To improve the survival prediction accuracy and help prognostic decision-making in clinical practice for medical experts, we for the first time propose a multimodal deep learning method for non-small cell lung cancer (NSCLC) survival analysis, named DeepMMSA.

44, TITLE: Task Transformer Network for Joint MRI Reconstruction and Super-Resolution
AUTHORS: Chun-Mei Feng ; Yunlu Yan ; Huazhu Fu ; Li Chen ; Yong Xu
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work, we propose an end-to-end task transformer network (T$^2$Net) for joint MRI reconstruction and super-resolution, which allows representations and feature transmission to be shared between multiple task to achieve higher-quality, super-resolved and motion-artifacts-free images from highly undersampled and degenerated MRI data.

45, TITLE: LE-NAS: Learning-based Ensenble with NAS for Dose Prediction
AUTHORS: YI LIN et. al.
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: In this study, we propose a novel learning-based ensemble approach, named LE-NAS, which integrates neural architecture search (NAS) with knowledge distillation for 3D radiotherapy dose prediction.

46, TITLE: Multi-level Attention Fusion Network for Audio-visual Event Recognition
AUTHORS: Mathilde Brousmiche ; Jean Rouat ; St�phane Dupont
CATEGORY: cs.CV [cs.CV, cs.MM]
HIGHLIGHT: In this study, we propose the Multi-level Attention Fusion network (MAFnet), an architecture that can dynamically fuse visual and audio information for event recognition.

47, TITLE: Magic Layouts: Structural Prior for Component Detection in User Interface Designs
AUTHORS: Dipu Manandhar ; Hailin Jin ; John Collomosse
CATEGORY: cs.CV [cs.CV, cs.HC, cs.LG]
HIGHLIGHT: We present Magic Layouts; a method for parsing screenshots or hand-drawn sketches of user interface (UI) layouts.

48, TITLE: Delving Deep Into The Generalization of Vision Transformers Under Distribution Shifts
AUTHORS: CHONGZHI ZHANG et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work, we provide a comprehensive study on the out-of-distribution generalization of ViTs.

49, TITLE: Reverse-engineer The Distributional Structure of Infant Egocentric Views for Training Generalizable Image Classifiers
AUTHORS: Satoshi Tsutsui ; David Crandall ; Chen Yu
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We analyze egocentric views of attended objects from infants.

50, TITLE: PolarStream: Streaming Lidar Object Detection and Segmentation with Polar Pillars
AUTHORS: Qi Chen ; Sourabh Vora ; Oscar Beijbom
CATEGORY: cs.CV [cs.CV, cs.RO]
HIGHLIGHT: In this work we propose using a polar coordinate system and make two key improvements on this design.

51, TITLE: A One-Shot Texture-Perceiving Generative Adversarial Network for Unsupervised Surface Inspection
AUTHORS: Lingyun Gu ; Lin Zhang ; Zhaokui Wang
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To combat it, we propose a hierarchical texture-perceiving generative adversarial network (HTP-GAN) that is learned from the one-shot normal image in an unsupervised scheme.

52, TITLE: Multistream ValidNet: Improving 6D Object Pose Estimation By Automatic Multistream Validation
AUTHORS: Joy Mazumder ; Mohsen Zand ; Michael Greenspan
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: This work presents a novel approach to improve the results of pose estimation by detecting and distinguishing between the occurrence of True and False Positive results.

53, TITLE: Object-Guided Instance Segmentation With Auxiliary Feature Refinement for Biological Images
AUTHORS: JINGRU YI et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose a novel box-based instance segmentation method.

54, TITLE: Sejong Face Database: A Multi-Modal Disguise Face Database
AUTHORS: Usman Cheema ; Seungbin Moon
CATEGORY: cs.CV [cs.CV, cs.AI, cs.LG]
HIGHLIGHT: In this paper, we present a multimodal disguised face dataset to facilitate the disguised face recognition research.

55, TITLE: Improved Transformer for High-Resolution GANs
AUTHORS: Long Zhao ; Zizhao Zhang ; Ting Chen ; Dimitris N. Metaxas ; Han Zhang
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we introduce two key ingredients to Transformer to address this challenge.

56, TITLE: Contrastive Semi-Supervised Learning for 2D Medical Image Segmentation
AUTHORS: PRASHANT PANDEY et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work, we present a novel semi-supervised 2D medical segmentation solution that applies CL on image patches, instead of full images.

57, TITLE: Group-based Bi-Directional Recurrent Wavelet Neural Networks for Video Super-Resolution
AUTHORS: Young-Ju Choi ; Young-Woon Lee ; Byung-Gyu Kim
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: In this paper, we propose a group-based bi-directional recurrent wavelet neural networks (GBR-WNN) to exploit the sequential data and spatio-temporal information effectively for VSR.

58, TITLE: Evaluating Foveated Video Quality Using Entropic Differencing
AUTHORS: Yize Jin ; Anjul Patney ; Alan Bovik
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: Towards advancing the progress of foveated video compression, we propose a full reference (FR) foveated image quality assessment algorithm, which we call foveated entropic differencing (FED), which employs the natural scene statistics of bandpass responses by applying differences of local entropies weighted by a foveation-based error sensitivity function.

59, TITLE: Video Super-Resolution Transformer
AUTHORS: Jiezhang Cao ; Yawei Li ; Kai Zhang ; Luc Van Gool
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we make the first attempt to adapt Transformer for VSR.

60, TITLE: User-Guided Personalized Image Aesthetic Assessment Based on Deep Reinforcement Learning
AUTHORS: PEI LV et. al.
CATEGORY: cs.CV [cs.CV, cs.MM, 94, H.5; I.4]
HIGHLIGHT: In order to acquire precise personalized aesthetic distribution by small amount of samples, we propose a novel user-guided personalized image aesthetic assessment framework.

61, TITLE: S$^2$-MLP: Spatial-Shift MLP Architecture for Vision
AUTHORS: Tan Yu ; Xu Li ; Yunfeng Cai ; Mingming Sun ; Ping Li
CATEGORY: cs.CV [cs.CV, cs.AI, cs.LG]
HIGHLIGHT: In this paper, we propose a novel pure MLP architecture, spatial-shift MLP (S$^2$-MLP).

62, TITLE: Comparing Vector Fields Across Surfaces: Interest for Characterizing The Orientations of Cortical Folds
AUTHORS: Amine Bohi ; Guillaume Auzias ; Julien Lef�vre
CATEGORY: cs.CV [cs.CV, math.DG, physics.bio-ph, physics.med-ph]
HIGHLIGHT: In this paper, we propose a framework to achieve this task by mapping the vector fields onto a common space, using some notions of differential geometry.

63, TITLE: Styleformer: Transformer Based Generative Adversarial Networks with Style Vector
AUTHORS: Jeeseung Park ; Younggeun Kim
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We propose Styleformer, which is a style-based generator for GAN architecture, but a convolution-free transformer-based generator.

64, TITLE: Reborn Mechanism: Rethinking The Negative Phase Information Flow in Convolutional Neural Network
AUTHORS: Zhicheng Cai ; Kaizhu Huang ; Chenglei Peng
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: This paper proposes a novel nonlinear activation mechanism typically for convolutional neural network (CNN), named as reborn mechanism.

65, TITLE: Generation of The NIR Spectral Band for Satellite Images with Convolutional Neural Networks
AUTHORS: Svetlana Illarionova ; Dmitrii Shadrin ; Alexey Trekin ; Vladimir Ignatiev ; Ivan Oseledets
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this research, we aim to investigate whether this approach can produce not only visually similar images but also an artificial spectral band that can improve the performance of computer vision algorithms for solving remote sensing tasks.

66, TITLE: Deep Transfer Learning for Brain Magnetic Resonance Image Multi-class Classification
AUTHORS: Yusuf Brima ; Mossadek Hossain Kamal Tushar ; Upama Kabir ; Tariqul Islam
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: In this research, we have curated a novel dataset and developed a framework that uses Deep Transfer Learning to perform a multi-classification of tumors in the brain MRI images.

67, TITLE: Variational Quanvolutional Neural Networks with Enhanced Image Encoding
AUTHORS: Denny Mattern ; Darya Martyniuk ; Henri Willems ; Fabian Bergmann ; Adrian Paschke
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we study the effect of three different quantum image encoding approaches on the performance of a convolution-inspired hybrid quantum-classical image classification algorithm called quanvolutional neural network (QNN).

68, TITLE: Reducing Effects of Swath Gaps on Unsupervised Machine Learning Models for NASA MODIS Instruments
AUTHORS: SARAH CHEN et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: Hence, we propose an augmentation technique that considerably removes the existence of swath gaps in order to allow CNNs to focus on the ROI, and thus successfully use data with swath gaps for training.

69, TITLE: Quality-Aware Network for Face Parsing
AUTHORS: Lu Yang ; Qing Song ; Xueshi Xin ; Zhiwei Liu
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: This is a very short technical report, which introduces the solution of the Team BUPT-CASIA for Short-video Face Parsing Track of The 3rd Person in Context (PIC) Workshop and Challenge at CVPR 2021.

70, TITLE: Inverting Adversarially Robust Networks for Image Synthesis
AUTHORS: Renan A. Rojas-Gomez ; Raymond A. Yeh ; Minh N. Do ; Anh Nguyen
CATEGORY: cs.CV [cs.CV, cs.LG, cs.NE]
HIGHLIGHT: This work proposes the use of robust representations as a perceptual primitive for feature inversion models, and show its benefits with respect to standard non-robust image features.

71, TITLE: Deep Learning for Reversible Steganography: Principles and Insights
AUTHORS: CHING-CHUN CHANG et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we investigate the modular framework and deploy deep neural networks in a reversible steganographic scheme referred to as prediction-error modulation, in which an analytics module serves the purpose of pixel intensity prediction.

72, TITLE: Siamese Network Training Using Sampled Triplets and Image Transformation
AUTHORS: Ammar N. Abbas ; David Moser
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: The device used in this work detects the objects over the surface of the water using two thermal cameras which aid the users to detect and avoid the objects in scenarios where the human eyes cannot (night, fog, etc.).

73, TITLE: Noise2Score: Tweedie's Approach to Self-Supervised Image Denoising Without Clean Images
AUTHORS: Kwanyoung Kim ; Jong Chul Ye
CATEGORY: cs.CV [cs.CV, cs.LG, stat.ML]
HIGHLIGHT: To address this, here we present a novel approach, called Noise2Score, which reveals a missing link in order to unite these seemingly different approaches.

74, TITLE: An Interaction-based Convolutional Neural Network (ICNN) Towards Better Understanding of COVID-19 X-ray Images
AUTHORS: Shaw-Hwa Lo ; Yiqiao Yin
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We propose a novel Interaction-based Convolutional Neural Network (ICNN) that does not make assumptions about the relevance of local information.

75, TITLE: A Multi-Implicit Neural Representation for Fonts
AUTHORS: PRADYUMNA REDDY et. al.
CATEGORY: cs.CV [cs.CV, cs.GR]
HIGHLIGHT: Based on the observation that complex fonts can be represented by a superposition of a set of simpler occupancy functions, we introduce \textit{multi-implicits} to represent fonts as a permutation-invariant set of learned implict functions, without losing features (e.g., edges and corners).

76, TITLE: Is Perfect Filtering Enough Leading to Perfect Phase Correction for DMRI Data?
AUTHORS: LIU FEIHONG et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work, after diving into the phase correction procedures, we argue that even a perfect filter is insufficient for phase correction because the correction procedures are incapable of distinguishing sign-symbols of noise, resulting in artifacts (\textit{i.e.}, arbitrary signal loss).

77, TITLE: NDPNet: A Novel Non-linear Data Projection Network for Few-shot Fine-gained Image Classification
AUTHORS: Weichuan Zhangy ; Xuefang Liuy ; Zhe Xue ; Yongsheng Gao ; Changming Sun
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: In this work, we propose, for the first time, to introduce the non-linear data projection concept into the design of FSFGIC architecture in order to address the limited sample problem in few-shot learning and at the same time to increase the discriminability of the model for fine-grained image classification.

78, TITLE: DyGLIP: A Dynamic Graph Model with Link Prediction for Accurate Multi-Camera Multiple Object Tracking
AUTHORS: KHA GIA QUACH et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To address these problems, this work, therefore, proposes a new Dynamic Graph Model with Link Prediction (DyGLIP) approach to solve the data association task.

79, TITLE: A Stronger Baseline for Ego-Centric Action Detection
AUTHORS: ZHIWU QING et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: This technical report analyzes an egocentric video action detection method we used in the 2021 EPIC-KITCHENS-100 competition hosted in CVPR2021 Workshop.

80, TITLE: Hyperspectral and Multispectral Classification for Coastal Wetland Using Depthwise Feature Interaction Network
AUTHORS: YUNHAO GAO et. al.
CATEGORY: cs.CV [cs.CV, cs.LG, eess.IV]
HIGHLIGHT: In this paper, the Deepwise Feature Interaction Network (DFINet) is proposed for wetland classification.

81, TITLE: Cross-Modal Attention Consistency for Video-Audio Unsupervised Learning
AUTHORS: SHAOBO MIN et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: This paper introduces a pretext task, Cross-Modal Attention Consistency (CMAC), for exploring the bidirectional local correspondence property.

82, TITLE: Pyramidal Dense Attention Networks for Lightweight Image Super-Resolution
AUTHORS: Huapeng Wu ; Jie Gui ; Jun Zhang ; James T. Kwok ; Zhihui Wei
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To solve this problem, we propose a pyramidal dense attention network (PDAN) for lightweight image super-resolution in this paper.

83, TITLE: The Spatio-Temporal Poisson Point Process: A Simple Model for The Alignment of Event Camera Data
AUTHORS: Cheng Gu ; Erik Learned-Miller ; Daniel Sheldon ; Guillermo Gallego ; Pia Bideau
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work we propose a new model of event data that captures its natural spatio-temporal structure.

84, TITLE: NLHD: A Pixel-Level Non-Local Retinex Model for Low-Light Image Enhancement
AUTHORS: Hou Hao ; Hou Yingkun ; Shi Yuxuan ; Wei Benzheng ; Xu Jun
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose a new pixel-level non-local Haar transform based illumination and reflectance decomposition method (NLHD).

85, TITLE: Feedback Pyramid Attention Networks for Single Image Super-Resolution
AUTHORS: Huapeng Wu ; Jie Gui ; Jun Zhang ; James T. Kwok ; Zhihui Wei
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose feedback pyramid attention networks (FPAN) to fully exploit the mutual dependencies of features.

86, TITLE: Contrastive Attention for Automatic Chest X-ray Report Generation
AUTHORS: FENGLIN LIU et. al.
CATEGORY: cs.CV [cs.CV, cs.CL]
HIGHLIGHT: In this work, to effectively capture and describe abnormal regions, we propose the Contrastive Attention (CA) model.

87, TITLE: Exploring and Distilling Posterior and Prior Knowledge for Radiology Report Generation
AUTHORS: Fenglin Liu ; Xian Wu ; Shen Ge ; Wei Fan ; Yuexian Zou
CATEGORY: cs.CV [cs.CV, cs.CL]
HIGHLIGHT: To this end, we propose a Posterior-and-Prior Knowledge Exploring-and-Distilling approach (PPKED) to imitate the working patterns of radiologists, who will first examine the abnormal regions and assign the disease topic tags to the abnormal regions, and then rely on the years of prior medical knowledge and prior working experience accumulations to write reports.

88, TITLE: Sparse PointPillars: Exploiting Sparsity in Birds-Eye-View Object Detection
AUTHORS: Kyle Vedder ; Eric Eaton
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: We present preliminary results demonstrating decreased runtimes with either the same performance or a modest decrease in performance, which we anticipate will be remedied by model specific hyperparameter tuning.

89, TITLE: Representation and Correlation Enhanced Encoder-Decoder Framework for Scene Text Recognition
AUTHORS: Mengmeng Cui ; Wei Wang ; Jinjin Zhang ; Liang Wang
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose a Representation and Correlation Enhanced Encoder-Decoder Framework(RCEED) to address these deficiencies and break performance bottleneck.

90, TITLE: Do Not Escape From The Manifold: Discovering The Local Coordinates on The Latent Space of GANs
AUTHORS: JAEWOONG CHOI et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose a method to find local-geometry-aware traversal directions on the intermediate latent space of Generative Adversarial Networks (GANs).

91, TITLE: Dilated Filters for Edge Detection Algorithms
AUTHORS: Ciprian Orhei ; Victor Bogdan ; Cosmin Bonchis
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work we try to put together all our previous and current results by using instead of the classical convolution filters a dilated one.

92, TITLE: Pixel Sampling for Style Preserving Face Pose Editing
AUTHORS: XIANGNAN YIN et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we take advantage of the well-known frontal/profile optical illusion and present a novel two-stage approach to solve the aforementioned dilemma, where the task of face pose manipulation is cast into face inpainting.

93, TITLE: Weakly-supervised High-resolution Segmentation of Mammography Images for Breast Cancer Diagnosis
AUTHORS: KANGNING LIU et. al.
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: In this work, we introduce a novel neural network architecture to perform weakly-supervised segmentation of high-resolution images.

94, TITLE: Computer Vision Tool for Detection, Mapping and Fault Classification of PV Modules in Aerial IR Videos
AUTHORS: LUKAS BOMMES et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work, we develop a computer vision tool for the semi-automatic extraction of PV modules from thermographic UAV videos.

95, TITLE: Robust Representation Learning Via Perceptual Similarity Metrics
AUTHORS: Saeid Asgari Taghanaki ; Kristy Choi ; Amir Khasahmadi ; Anirudh Goyal
CATEGORY: cs.LG [cs.LG, cs.CV]
HIGHLIGHT: In this work, we propose Contrastive Input Morphing (CIM), a representation learning framework that learns input-space transformations of the data to mitigate the effect of irrelevant input features on downstream performance.

96, TITLE: PopSkipJump: Decision-Based Attack for Probabilistic Classifiers
AUTHORS: Carl-Johann Simon-Gabriel ; Noman Ahmed Sheikh ; Andreas Krause
CATEGORY: cs.LG [cs.LG, cs.CR, cs.CV, math.OC, stat.ML]
HIGHLIGHT: We therefore propose a new adversarial decision-based attack specifically designed for classifiers with probabilistic outputs.

97, TITLE: Federated Learning with Spiking Neural Networks
AUTHORS: Yeshwanth Venkatesha ; Youngeun Kim ; Leandros Tassiulas ; Priyadarshini Panda
CATEGORY: cs.LG [cs.LG, cs.CV, cs.NE]
HIGHLIGHT: In this paper, we bring SNNs to a more realistic federated learning scenario.

98, TITLE: Unsupervised Learning of Visual 3D Keypoints for Control
AUTHORS: Boyuan Chen ; Pieter Abbeel ; Deepak Pathak
CATEGORY: cs.LG [cs.LG, cs.CV, cs.RO]
HIGHLIGHT: In this work, we propose a framework to learn such a 3D geometric structure directly from images in an end-to-end unsupervised manner.

99, TITLE: Knowledge Consolidation Based Class Incremental Online Learning with Limited Data
AUTHORS: Mohammed Asad Karim ; Vinay Kumar Verma ; Pravendra Singh ; Vinay Namboodiri ; Piyush Rai
CATEGORY: cs.LG [cs.LG, cs.AI, cs.CV]
HIGHLIGHT: We propose a novel approach for class incremental online learning in a limited data setting.

100, TITLE: Adversarial Robustness Via Fisher-Rao Regularization
AUTHORS: MARINE PICOT et. al.
CATEGORY: cs.LG [cs.LG, cs.CV]
HIGHLIGHT: We propose an information-geometric formulation of adversarial defense and introduce FIRE, a new Fisher-Rao regularization for the categorical cross-entropy loss, which is based on the geodesic distance between natural and perturbed input features.

101, TITLE: D2C: Diffusion-Denoising Models for Few-shot Conditional Generation
AUTHORS: Abhishek Sinha ; Jiaming Song ; Chenlin Meng ; Stefano Ermon
CATEGORY: cs.LG [cs.LG, cs.AI, cs.CV]
HIGHLIGHT: This paper describes Diffusion-Decoding models with Contrastive representations (D2C), a paradigm for training unconditional variational autoencoders (VAEs) for few-shot conditional image generation.

102, TITLE: Non Gaussian Denoising Diffusion Models
AUTHORS: Eliya Nachmani ; Robin San Roman ; Lior Wolf
CATEGORY: cs.LG [cs.LG, cs.AI, cs.CV, cs.SD]
HIGHLIGHT: In this work, we investigate other types of noise distribution for the diffusion process.

103, TITLE: Full Interpretable Machine Learning in 2D with Inline Coordinates
AUTHORS: Boris Kovalerchuk ; Hoang Phan
CATEGORY: cs.LG [cs.LG, cs.CV]
HIGHLIGHT: This paper proposed a new methodology for machine learning in 2-dimensional space (2-D ML) in inline coordinates.

104, TITLE: Latent Correlation-Based Multiview Learning and Self-Supervision: A Unifying Perspective
AUTHORS: Qi Lyu ; Xiao Fu ; Weiran Wang ; Songtao Lu
CATEGORY: cs.LG [cs.LG, cs.AI, cs.CV, stat.ML]
HIGHLIGHT: Our development starts with proposing a multiview model, where each view is a nonlinear mixture of shared and private components.

105, TITLE: Adaptive Dynamic Pruning for Non-IID Federated Learning
AUTHORS: Sixing Yu ; Phuong Nguyen ; Ali Anwar ; Ali Jannesari
CATEGORY: cs.LG [cs.LG, cs.CV]
HIGHLIGHT: In this paper, we present an adaptive pruning scheme for edge devices in an FL system, which applies dataset-aware dynamic pruning for inference acceleration on Non-IID datasets.

106, TITLE: Boosting Randomized Smoothing with Variance Reduced Classifiers
AUTHORS: Mikl�s Z. Horv�th ; Mark Niklas M�ller ; Marc Fischer ; Martin Vechev
CATEGORY: cs.LG [cs.LG, cs.AI, cs.CV]
HIGHLIGHT: The key insight of our work is that the reduced variance of ensembles over the perturbations introduced in RS leads to significantly more consistent classifications for a given input, in turn leading to substantially increased certifiable radii for difficult samples.

107, TITLE: A Novel Mapping for Visual to Auditory Sensory Substitution
AUTHORS: Ezsan Mehrbani ; Sezedeh Fatemeh Mirhoseini ; Noushin Riahi
CATEGORY: cs.SD [cs.SD, cs.AI, cs.CV]
HIGHLIGHT: In this study, visual environmental features namely, coordinate, type of objects and their size are assigned to audio features related to music tones such as frequency, time duration and note permutations.

108, TITLE: Rapid COVID-19 Risk Screening By Eye-region Manifestations
AUTHORS: YANWEI FU et. al.
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: Meantime as an important part of the ongoing globally COVID-19 eye test program by AIMOMICS since February 2020, we propose a new fast screening method of analyzing the eye-region images, captured by common CCD and CMOS cameras.

109, TITLE: Hippocampus Segmentation in Magnetic Resonance Images of Alzheimer's Patients Using Deep Machine Learning
AUTHORS: Hadi Varmazyar ; Hossein Yousefi-Banaem ; Saber Malekzadeh ; Nahideh Gharehaghaji
CATEGORY: eess.IV [eess.IV, cs.CV, cs.LG, q-bio.NC]
HIGHLIGHT: Objective: The aim of this study was the segmentation of the hippocampus in magnetic resonance (MR) images of Alzheimers patients using deep machine learning method.

110, TITLE: Recursive Refinement Network for Deformable Lung Registration Between Exhale and Inhale CT Scans
AUTHORS: XINZI HE et. al.
CATEGORY: eess.IV [eess.IV, cs.AI, cs.CV, cs.LG]
HIGHLIGHT: We propose to revisit a commonly ignored while simple and well-established principle: recursive refinement of deformation vector fields across scales.

111, TITLE: MIA-COV19D: COVID-19 Detection Through 3-D Chest CT Image Analysis
AUTHORS: Dimitrios Kollias ; Anastasios Arsenos ; Levon Soukissian ; Stefanos Kollias
CATEGORY: eess.IV [eess.IV, cs.CV, cs.LG]
HIGHLIGHT: In this paper we present the COV19-CT-DB database which is annotated for COVID-19, consisting of about 5,000 3-D CT scans, We have split the database in training, validation and test datasets.

112, TITLE: Learning The Imaging Landmarks: Unsupervised Key Point Detection in Lung Ultrasound Videos
AUTHORS: ARPAN TRIPATHI et. al.
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: We adapted the relatively newer approach of transporter neural networks to automatically mark and track pleura, A and B lines based on their periodic motion and relatively stable appearance in the videos.

113, TITLE: An Approach Towards Physics Informed Lung Ultrasound Image Scoring Neural Network for Diagnostic Assistance in COVID-19
AUTHORS: MAHESH RAVEENDRANATHA PANICKER et. al.
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: In this work, a novel approach is presented to extract acoustic propagation-based features to automatically highlight the region below pleura, which is an important landmark in lung ultrasound (LUS).

计算机视觉论文-2021-06-15相关推荐

数据分析task01（2021.06.15）
1 第一章:数据载入及初步观察 1.1 载入数据 1.1.1 任务一:导入numpy和pandas import numpy as np import pandas as pd 1.1.2 任务二:载 ...
《惢客创业日记》2021.06.15（周二）凉粉儿的防骗三板斧
今天,凉粉儿给我打了个电话,告诉我一个消息,说是有一个投资机构对我们惢客项目感兴趣,想聊聊.说实话,有了上一次"深圳行"的经历,我和凉粉儿都怕了,为此,我还在2021年3月2日写下 ...
【AI视野·今日CV 计算机视觉论文速览第219期】Tue, 15 Jun 2021
AI视野·今日CS.CV 计算机视觉论文速览 Tue, 15 Jun 2021 (showing first 100 of 128 entries) Totally 100 papers
2021年必读的10 个计算机视觉论文总结
点击上方"3D视觉工坊",选择"星标" 干货第一时间送达作者丨Louis Bouchard 来源丨DeepHub IMBA 编辑丨极市平台本文是作者总结的今 ...
【AI视野·今日CV 计算机视觉论文速览第244期】Fri, 15 Apr 2022
AI视野·今日CS.CV 计算机视觉论文速览 Fri, 15 Apr 2022 Totally 70 papers
【AI视野·今日CV 计算机视觉论文速览第240期】Thu, 4 Nov 2021
AI视野·今日CS.CV 计算机视觉论文速览 Thu, 4 Nov 2021 Totally 35 papers
【AI视野·今日CV 计算机视觉论文速览第239期】Wed, 3 Nov 2021
AI视野·今日CS.CV 计算机视觉论文速览 Wed, 3 Nov 2021 Totally 48 papers
【AI视野·今日CV 计算机视觉论文速览第238期】Fri, 1 Oct 2021
AI视野·今日CS.CV 计算机视觉论文速览 Fri, 1 Oct 2021 Totally 62 papers
【AI视野·今日CV 计算机视觉论文速览第237期】Thu, 30 Sep 2021
AI视野·今日CS.CV 计算机视觉论文速览 Thu, 30 Sep 2021 Totally 47 papers
【AI视野·今日CV 计算机视觉论文速览第233期】Tue, 3 Aug 2021
AI视野·今日CS.CV 计算机视觉论文速览 Tue, 3 Aug 2021 Totally xx papers

计算机视觉论文-2021-06-15

计算机视觉论文-2021-06-15相关推荐

最新文章

热门文章