Dynamic Template Initialization for Part-Aware Person Re-ID

TL;DR

This paper proposes a dynamic, attention-based method for initializing part templates in person re-identification, improving robustness to occlusions and partial views by adapting to input-specific features.

Contribution

It introduces a novel spatial attention-based dynamic template initialization module that generates part templates from mid-level features, enhancing discriminative power in challenging scenarios.

Findings

Achieves competitive performance on various Re-ID benchmarks.

Effectively handles occlusions and partial views.

Demonstrates improved robustness over static template methods.

Abstract

Many of the existing Person Re-identification (Re-ID) approaches depend on feature maps which are either partitioned to localize parts of a person or reduced to create a global representation. While part localization has shown significant success, it uses either na{\i}ve position-based partitions or static feature templates. These, however, hypothesize the pre-existence of the parts in a given image or their positions, ignoring the input image-specific information which limits their usability in challenging scenarios such as Re-ID with partial occlusions and partial probe images. In this paper, we introduce a spatial attention-based Dynamic Part Template Initialization module that dynamically generates part-templates using mid-level semantic features at the earlier layers of the backbone. Following a self-attention layer, human part-level features of the backbone are used to extract the templates of diverse human body parts using a simplified cross-attention scheme which will then be used to identify and collate representations of various human parts from semantically rich features, increasing the discriminative ability of the entire model. We further explore adaptive weighting of part descriptors to quantify the absence or occlusion of local attributes and suppress the contribution of the corresponding part descriptors to the matching criteria. Extensive experiments on holistic, occluded, and partial Re-ID task benchmarks demonstrate that our proposed architecture is able to achieve competitive performance. Codes will be included in the supplementary material and will be made publicly available.