论文

论文题目：Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detection*

收录：CVPR2022

论文地址：[2203.14506] Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detection (arxiv.org)

项目地址：GitHub - Choubo/DRA: Official PyTorch implementation of the paper “Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detection”, open-set anomaly detection, few-shot anomaly detection.

论文翻译：Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detection_appron的博客-CSDN博客

本文讲的是关于开放数据集上图像异常检测的问题，文中将很多知识框架信息都隐去了，想具体了解的可以先看另一篇论文《Deep Anomaly Detection with Deviation Networks》，几篇解读写的很明白，看完后就基本能理解本文的框架了。

《Deep Anomaly Detection with Deviation Networks》

论文来源｜ KDD 2019
论文链接｜ [1911.08623] Deep Anomaly Detection with Deviation Networks (arxiv.org)
源码链接｜ GitHub - GuansongPang/deviation-network: Source code of the KDD19 paper "Deep anomaly detection with deviation networks", weakly/partially supervised anomaly detection, few-shot anomaly detection

论文解读 | DevNet：基于偏差网络的深度异常检测模型 | 梦家博客 (dreamhomes.top)

论文分享 | Deep Anomaly Detection with Deviation Networks (qq.com)

DevNet半监督异常识别模型 - 知乎 (zhihu.com)

整体框架图解读：Deep Anomaly Detection with Deviation Networks

论文解读 Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detection*

数据集展示

论文改进

主要内容&贡献

关键点

【读论文04】CVPR2022选读_要谦年人的博客-CSDN博客

问题定义

思路

框架

代码解读

4个head

数据预处理

可见异常样本读取

伪异常样本生成

模型输入

解耦异常得分

返回值

Loss

BEC Loss、Focal Loss和Dev Loss的比较

分离异常学习，各head的loss

实验

实验细节

普通设定结果

困难设定结果

消融实验

每个异常学习head的重要性

伪异常样本生成方式比较

解耦学习的重要性及参考图像数量比较

【论文笔记】Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detection*相关推荐

论文笔记 ISCC 2019|BGP Dataset Generation and Feature Extraction for Anomaly Detection
文章目录 1 简介 1.1 动机 1.2 创新 2 背景知识 3 方法 3.1 特征提取 3.2 数据集生成 3.3 流量行为趋势分析 3.3.1 Anomaly and regular traffi ...
【阅读笔记】《Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detection》
Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detection 文章目录 Catching Both Gray an ...
Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detection
Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detection 摘要尽管大多数现有的异常检测研究只假设有正常的训练 ...
【论文笔记】Hierarchical Paired Channel Fusion Network for Street Scene Change Detection
论文论文题目:Hierarchical Paired Channel Fusion Network for Street Scene Change Detection 收录:IEEE Transac ...
论文笔记-Suppress and Balance: A Simple Gated Network for Salient Object Detection
Hello, 今天是论文阅读计划的第19天啦- 也是我在这30天中要介绍的最后一篇目标检测的论文啦一.背景最显著的目标检测方法使用的基本结构是三角网或特征金字塔网络(FPN).这些方法忽略了编码器 ...
论文笔记-DeepLung: Deep 3D Dual Path Nets for Automated Pulmonary Nodule Detection and Classification
这篇论文来自与加州大学欧文分校,百度研究和腾讯AI医学AI实验室. 该论文提出了一整套自动检测和分类肺结节的系统.系统架构如下图: 前半部分为肺结节检测系统,采用3D Faster R-CNN网络来检 ...
【论文笔记】—毫米波雷达穿雾式高分辨率成像—Supervised—HawkEye系统—2020-CVPR
题目:Through Fog High-Resolution Imaging Using Millimeter Wave Radar 利用毫米波雷达进行穿雾式高分辨率成像 DOI:10.1109/CV ...
【论文笔记】Exploring Temporal Coherence for More General Video Face Forgery Detection
* Exploring Temporal Coherence for More General Video Face Forgery Detection 题目:探索更一般的视频人脸伪造检测的时间相干性 ...
论文笔记-F3Net：Fusion, Feedback and Focus for Salient Object Detection
论文笔记之2020-AAAI-F3Net-F3Net:Fusion, Feedback and Focus for Salient Object Detection 论文地址:https://arxi ...

【论文笔记】Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detection*

论文