Erasing, Transforming, and Noising Defense Network for Occluded Person Re-Identification
Preprint
Abstract
Occlusion perturbation presents a significant challenge in person re-identification (re-ID), and existing methods that rely on external visual cues require additional computational resources and only consider the issue of missing information caused by occlusion. In this paper, we propose a simple yet effective framework, termed Erasing, Transforming, and Noising Defense Network (ETNDNet), which treats occlusion as a noise disturbance and solves occluded person re-ID from the perspective of adversarial defense. In the proposed ETNDNet, we introduce three strategies: Firstly, we randomly erase the feature map to create an adversarial representation with incomplete information, enabling adversarial learning of identity loss to protect the re-ID system from the disturbance of missing information. Secondly, we introduce random transformations to simulate the position misalignment caused by occlusion, training the extractor and classifier adversarially to learn robust representations immune to misaligned information. Thirdly, we perturb the feature map with random values to address noisy information introduced by obstacles and non-target pedestrians, and employ adversarial gaming in the re-ID system to enhance its resistance to occlusion noise. Without bells and whistles, ETNDNet has three key highlights: (i) it does not require any external modules with parameters, (ii) it effectively handles various issues caused by occlusion from obstacles and non-target pedestrians, and (iii) it designs the first GAN-based adversarial defense paradigm for occluded person re-ID. Extensive experiments on five public datasets fully demonstrate the effectiveness, superiority, and practicality of the proposed ETNDNet. The code will be released at \url{https://github.com/nengdong96/ETNDNet}.Keywords
All Related Versions
This publication has 17 references indexed in Scilit:
- Reasoning and Tuning: Graph Attention Network for Occluded Person Re-IdentificationIEEE Transactions on Image Processing, 2023
- Occluded Person Re-Identification via Defending Against Attacks From ObstaclesIEEE Transactions on Information Forensics and Security, 2022
- MHSA-Net: Multihead Self-Attention Network for Occluded Person Re-IdentificationIEEE Transactions on Neural Networks and Learning Systems, 2022
- Quality-Aware Part Models for Occluded Person Re-IdentificationIEEE Transactions on Multimedia, 2022
- Learning Disentangled Representation Implicitly Via Transformer for Occluded Person Re-IdentificationIEEE Transactions on Multimedia, 2022
- Beyond Universal Person Re-Identification AttackIEEE Transactions on Information Forensics and Security, 2021
- Incremental Generative Occlusion Adversarial Suppression Network for Person ReIDIEEE Transactions on Image Processing, 2021
- Identifying Visible Parts via Pose Estimation for Occluded Person Re-IdentificationIEEE Transactions on Neural Networks and Learning Systems, 2021
- Deep Learning for LiDAR Point Clouds in Autonomous Driving: A ReviewIEEE Transactions on Neural Networks and Learning Systems, 2020
- Multi-Commodity Network Flow for Tracking Multiple PeopleIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013