Semantic-guided Pixel Sampling for Cloth-Changing Person Re-identification

07/24/2021
by   Xiujun Shu, et al.
0

Cloth-changing person re-identification (re-ID) is a new rising research topic that aims at retrieving pedestrians whose clothes are changed. This task is quite challenging and has not been fully studied to date. Current works mainly focus on body shape or contour sketch, but they are not robust enough due to view and posture variations. The key to this task is to exploit cloth-irrelevant cues. This paper proposes a semantic-guided pixel sampling approach for the cloth-changing person re-ID task. We do not explicitly define which feature to extract but force the model to automatically learn cloth-irrelevant cues. Specifically, we first recognize the pedestrian's upper clothes and pants, then randomly change them by sampling pixels from other pedestrians. The changed samples retain the identity labels but exchange the pixels of clothes or pants among different pedestrians. Besides, we adopt a loss function to constrain the learned features to keep consistent before and after changes. In this way, the model is forced to learn cues that are irrelevant to upper clothes and pants. We conduct extensive experiments on the latest released PRCC dataset. Our method achieved 65.8 which outperforms previous methods with a large margin. The code is available at https://github.com/shuxjweb/pixel_sampling.git.

READ FULL TEXT

page 1

page 2

page 4

research
04/14/2022

Clothes-Changing Person Re-identification with RGB Modality Only

The key to address clothes-changing person re-identification (re-id) is ...
research
08/27/2023

Semantic-aware Consistency Network for Cloth-changing Person Re-Identification

Cloth-changing Person Re-Identification (CC-ReID) is a challenging task ...
research
04/10/2023

Identity-Guided Collaborative Learning for Cloth-Changing Person Reidentification

Cloth-changing person reidentification (ReID) is a newly emerging resear...
research
07/18/2022

A Semantic-aware Attention and Visual Shielding Network for Cloth-changing Person Re-identification

Cloth-changing person reidentification (ReID) is a newly emerging resear...
research
07/27/2020

Identity-Guided Human Semantic Parsing for Person Re-Identification

Existing alignment-based methods have to employ the pretrained human par...
research
07/14/2023

Erasing, Transforming, and Noising Defense Network for Occluded Person Re-Identification

Occlusion perturbation presents a significant challenge in person re-ide...
research
11/17/2020

Towards All-around Knowledge Transferring: Learning From Task-irrelevant Labels

Deep neural models have hitherto achieved significant performances on nu...

Please sign up or login with your details

Forgot password? Click here to reset