Hi-CMD: Hierarchical Cross-Modality Disentanglement for Visible-Infrared Person Re-Identification
Authors:
- 1 June 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 10254-10263
Abstract
Visible-infrared person re-identification (VI-ReID) is an important task in night-time surveillance applications, since visible cameras are difficult to capture valid appearance information under poor illumination conditions. Compared to traditional person re-identification that handles only the intra-modality discrepancy, VI-ReID suffers from additional cross-modality discrepancy caused by different types of imaging systems. To reduce both intra- and cross-modality discrepancies, we propose a Hierarchical Cross-Modality Disentanglement (Hi-CMD) method, which automatically disentangles ID-discriminative factors and ID-excluded factors from visible-thermal images. We only use ID-discriminative factors for robust cross-modality matching without ID-excluded factors such as pose or illumination. To implement our approach, we introduce an ID-preserving person image generation network and a hierarchical feature learning module. Our generation network learns the disentangled representation by generating a new cross-modality image with different poses and illuminations while preserving a person's identity. At the same time, the feature learning module enables our model to explicitly extract the common ID-discriminative characteristic between visible-infrared images. Extensive experimental results demonstrate that our method outperforms the state-of-the-art methods on two VI-ReID datasets. The source code is available at: https://github.com/bismex/HiCMD.Keywords
All Related Versions
This publication has 30 references indexed in Scilit:
- RGB-Infrared Cross-Modality Person Re-identification2017
- SVDNet for Pedestrian Retrieval2017
- Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks2017
- Disentangled Representation Learning GAN for Pose-Invariant Face Recognition2017
- Person Recognition System Based on a Combination of Body Images from Visible Light and Thermal CamerasSensors, 2017
- Deep Perceptual Mapping for Cross-Modal Face RecognitionInternational Journal of Computer Vision, 2016
- Deep Residual Learning for Image Recognition2016
- Cross-Domain Visual Matching via Generalized Similarity Measure and Feature LearningIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- Person re-identification by Local Maximal Occurrence representation and metric learning2015
- Histograms of Oriented Gradients for Human Detection2005