Dual-Adversarial Representation Disentanglement for Visible Infrared Person Re-Identification
- 18 December 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 19 (15566013) , 2186-2200
Abstract
Heterogeneous pedestrian images are captured by visible and infrared cameras with different spectrums, which play an important role in night-time video surveillance. However, visible infrared person re-identification (VI-REID) is still a challenging problem due to the considerable cross-modality discrepancies. To extract modality-invariant features which are discriminative for the person identity, recent studies are inclined to regard modality-specific features as noise and discard them. Actually, the modality-specific characteristics containing background and color information are indispensable for learning modality-shared features. In this paper, we propose a novel Dual-Adversarial Representation Disentanglement (DARD) model to separate modality-specific features from tangled pedestrian representations and effectively learn the robust modality-invariant representations. Specifically, our method employs dual-adversarial learning, incorporating image-level channel exchange and feature-level magnitude change to introduce variations in modality-specific representations. This deliberate perturbation raises the learning difficulty for the model to learn modality-shared features. Simultaneously, to control the changing scope of modality-specific features, bi-constrained noise alleviation is introduced during adversarial learning, keeping the balance of feature generation and adversary. The proposed dual-adversarial learning methodology enhances the robustness against cross-modality visual discrepancy and strengthens the discriminative power of the learned modality-shared representations without introducing additional network parameters. This improvement further elevates the retrieval performance of VI-REID. Extensive experiments with insightful analysis on two cross-modality re-identification datasets verify the effectiveness and superiority of the proposed DARD method.Keywords
Funding Information
- National Natural Science Foundation of China (62372348, 62036007, U22A2096, U21A20514)
- Shaanxi Outstanding Youth Science Fund Project (2023-JC-JQ-53)
- Technology Innovation Leading Program of Shaanxi (2022QFY01-15)
- Fundamental Research Funds for the Central Universities (QTZX23042)
- Open Research Projects of Zhejiang Laboratory (2021KG0AB01)
This publication has 70 references indexed in Scilit:
- Bi-Directional Center-Constrained Top-Ranking for Visible Thermal Person Re-IdentificationIEEE Transactions on Information Forensics and Security, 2019
- Beyond Part Models: Person Retrieval with Refined Part Pooling (and A Strong Convolutional Baseline)2018
- An Adversarial Approach to Hard Triplet Generation2018
- Cross-Modality Person Re-Identification with Generative Adversarial Training2018
- Visible Thermal Person Re-Identification via Dual-Constrained Top-Ranking2018
- Dual Attention Matching Network for Context-Aware Feature Sequence Based Person Re-identification2018
- RGB-Infrared Cross-Modality Person Re-identification2017
- Beyond Triplet Loss: A Deep Quadruplet Network for Person Re-identification2017
- Person Recognition System Based on a Combination of Body Images from Visible Light and Thermal CamerasSensors, 2017
- Person Re-identification by Multi-Channel Parts-Based CNN with Improved Triplet Loss Function2016