【今日CV 视觉论文速览】 13 Feb 2019

今日CS.CV计算机视觉论文速览
Wed, 13 Feb 2019
Totally 26 papers

Interesting:

基于自编码器和隐空间编码的图像生成，通过直接估计隐变量的分布来利用自编码器生成图像。引入了能精确捕捉隐变量特征和结构的隐密度估计器，同时还引入了增量学习策略来帮助自编码器从数据中学习到重要特征，也利用了自编码器的结构特征。(from 首尔国立大学)
隐密度估计器：

采样逐渐趋近于目标分布：

一些生成的结果：

? MaCow, 基于流的掩膜卷积图像生成模型.。这篇文章提出了一种基于掩膜的流生成模型，提高了流生成模型的效率。通过利用小核来限制局域链接，MaCow保持了训练时的速度和稳定，以及有效的采样，并大大超过了Glow的密度估计水平，缩小了与自回归模型间的差距。(from CMU)
两个掩膜卷积的感受野：

模型单元步骤如下：

流生成模型与自回归模型的表现比较：

ref:
Glow
基于流，博客， Autoregressive Models

? Bag of Freebies 一系列训练技术提高现有目标检测的精度, 由于在多目标检测任务中对于空间保留变换具有较好的偏好，所以提出了视觉内容叠加混合来提高目标检测的精度。随后探索了训练流程，包括学习率调度、权重衰减和BN等，并验证了这些方法在训练中的有效性。(from 亚马逊)

通过混合图像训练后更鲁棒：

COCO

? Psi-Net, 用于分割的网络中引入了轮廓和距离图估计来作为正则项辅助训练。（from IITM）

论文中提出的单编码器并行解码器的结构，除了mask外还增加了轮廓和距离图的辅助任务：

Origa dataset for the task of optic cup and disc segmentation, paper
Endovis segment dataset for the task of polyp segmentation，paper
Diabetic Retinopathy Detection, git ref
ref1 zhihu, medicalmind datasets, opentracking.

? 用于自动驾驶的深度图语义图融合控制，利用深度图和视觉的语义分割图共同驾驶，多传感器的融合提高了系统的准确性和冗余性。(TMU)

基于条件网络的融合/基于权重的融合模型：

ref:室内机器人的RGB和激光雷达深度融合

Daily Computer Vision Papers

[1] Title: Center of circle after perspective transformation
Authors:Xi Wang, Albert Chern, Marc Alexa
[2] *Title: Fast-SCNN: Fast Semantic Segmentation Network
Authors:Rudra P K Poudel, Stephan Liwicki, Roberto Cipolla
[3] Title: Extended 2D Volumetric Consensus Hippocampus Segmentation
Authors:Diedre Carmo, Bruna Silva, Clarissa Yasuda, Letícia Rittner, Roberto Lotufo
[4] *Title: MASC: Multi-scale Affinity with Sparse Convolution for 3D Instance Segmentation
Authors:Chen Liu, Yasutaka Furukawa
[5] *Title: Manifestation of Image Contrast in Deep Networks
Authors:Arash Akbarinia, Karl R. Gegenfurtner
[6] Title: The effect of scene context on weakly supervised semantic segmentation
Authors:Mohammad Kamalzare, Reza Kahani, Alireza Talebpour, Ahmad Mahmoudi-Aznaveh
[7] *Title: GAN- vs. JPEG2000 Image Compression for Distributed Automotive Perception: Higher Peak SNR Does Not Mean Better Semantic Segmentation
Authors:Jonas Löhdefink, Andreas Bär, Nico M. Schmidt, Fabian Hüger, Peter Schlicht, Tim Fingscheidt
[8] *Title: A system for generating complex physically accurate sensor images for automotive applications
Authors:Zhenyi Liu, Minghao Shen, Jiaqi Zhang, Shuangting Liu, Henryk Blasinski, Trisha Lian, Brian Wandell
[9] *Title: Enhancement Mask for Hippocampus Detection and Segmentation
Authors:Dengsheng Chen, Wenxi Liu, You Huang, Tong Tong, Yuanlong Yu
[10] *Title: RespNet: A deep learning model for extraction of respiration from photoplethysmogram
Authors:Vignesh Ravichandran, Balamurali Murugesan, Vaishali Balakarthikeyan, Sharath M Shankaranarayana, Keerthi Ram, Preejith S.P, Jayaraj Joseph, Mohanasankar Sivaprakasam
[11] *Title: You Only Look & Listen Once: Towards Fast and Accurate Visual Grounding
Authors:Chaorui Deng, Qi Wu, Guanghui Xu, Zhuliang Yu, Yanwu Xu, Kui Jia, Mingkui Tan
[12] Title: Brain MRI Segmentation using Rule-Based Hybrid Approach
Authors:Mustansar Fiaz, Kamran Ali, Abdul Rehman, M. Junaid Gul, Soon Ki Jung
[13] *Title: De-identification without losing faces
Authors:Yuezun Li, Siwei Lyu
[14] Title: Riemannian joint dimensionality reduction and dictionary learning on symmetric positive definite manifold
Authors:Hiroyuki Kasai, Bamdev Mishra
[15] *Title: ReStoCNet: Residual Stochastic Binary Convolutional Spiking Neural Network for Memory-Efficient Neuromorphic Computing
Authors:Gopalakrishnan Srinivasan, Kaushik Roy
[16] Title: Learning to Authenticate with Deep Multibiometric Hashing and Neural Network Decoding
Authors:Veeru Talreja, Sobhan Soleymani, Matthew C. Valenti, Nasser M. Nasrabadi
[17] Title: Synthesizing New Retinal Symptom Images by Multiple Generative Models
Authors:Yi-Chieh Liu, Hao-Hsiang Yang, Chao-Han Huck Yang, Jia-Hong Huang, Meng Tian, Hiromasa Morikawa, Yi-Chang James Tsai, Jesper Tegner
[18] *Title: Max-C and Min-D Projection Autoassociative Fuzzy Morphological Memories: Theory and Applications for Face Recognition
Authors:Alex Santana dos Santos, Marcos Eduardo Valle
[19] Title: Using Deep Cross Modal Hashing and Error Correcting Codes for Improving the Efficiency of Attribute Guided Facial Image Retrieval
Authors:Veeru Talreja, Fariborz Taherkhani, Matthew C. Valenti, Nasser M. Nasrabadi
[20] *Title: Bag of Freebies for Training Object Detection Neural Networks
Authors:Zhi Zhang, Tong He, Hang Zhang, Zhongyuan Zhang, Junyuan Xie, Mu Li
[21] *Title: Psi-Net: Shape and boundary aware joint multi-task deep network for medical image segmentation
Authors:Balamurali Murugesan, Kaushik Sarveswaran, Sharath M Shankaranarayana, Keerthi Ram, Mohanasankar Sivaprakasam
[22] *Title: Joint Training of Neural Network Ensembles
Authors:Andrew M. Webb, Charles Reynolds, Dan-Andrei Iliescu, Henry Reeve, Mikel Lujan, Gavin Brown
[23] *Title: Density Estimation and Incremental Learning of Latent Vector for Generative Autoencoders
Authors:Jaeyoung Yoo, Hojun Lee, Nojun Kwak
[24] *Title: Towards Self-Supervised High Level Sensor Fusion
Authors:Qadeer Khan, Torsten Schön, Patrick Wenzel
[25] **Title: MaCow: Masked Convolutional Generative Flow
Authors:Xuezhe Ma, Eduard Hovy
[26] **Title: Iteratively reweighted penalty alternating minimization methods with continuation for image deblurring
Authors:Tao Sun, Dongsheng Li, Hao Jiang, Zhe Quan

Papers from arxiv.org

更多精彩请移步主页

pic from pixels.com
emoji：http://www.unicode.org/charts/
http://unicode.org/emoji/charts/full-emoji-list.html#1f449