Can I read A Deep Hierarchical Feature Sparse Framework for Occluded Person Re-Identification on EtoBox?

A Deep Hierarchical Feature Sparse Framework for Occluded Person Re-Identification by Song, Yihu; Liu, Shuaishi is a scholarly article available to read on EtoBox.

What is A Deep Hierarchical Feature Sparse Framework for Occluded Person Re-Identification about?

Most existing methods tackle the problem of occluded person re-identification (ReID) by utilizing auxiliary models, resulting in a complicated and inefficient ReID framework that is unacceptable for real-time applications. In this work, a speed-up person ReID framework named SUReID is proposed to mitigate occlusion interference while speeding up inference. The SUReID consists of three key components: hierarchical token sparsification (HTS) strategy, non-parametric feature alignment knowledge distillation (NPKD), and noise occlusion data augmentation (NODA). The HTS strategy works by pruning the redundant tokens in the vision transformer to achieve highly effective self-attention computation and eliminate interference from occlusions or background noise. However, the pruned tokens may contain human part features that contaminate the feature representation and degrade the performance. To solve this problem, the NPKD is employed to supervise the HTS strategy, retaining more discriminative tokens and discarding meaningless ones. Furthermore, the NODA is designed to introduce more noisy samples, which further trains the ability of the HTS to disentangle different tokens. Experimental re

Author

Song, Yihu; Liu, Shuaishi

Published

2024

Language

EN