Instance and Pair-Aware Dynamic Networks for Re-Identification

TL;DR

This paper introduces a novel dynamic convolution framework for re-identification that enhances feature extraction by considering both individual image details and pairwise relevance, leading to improved accuracy across multiple datasets.

Contribution

The paper proposes an end-to-end trainable dynamic network with instance and pair-aware branches, addressing the gap of relevance exploration between images in ReID tasks.

Findings

Outperforms state-of-the-art on several datasets

Achieves comparable performance on others

Demonstrates effectiveness of dynamic, relevance-aware features

Abstract

Re-identification (ReID) is to identify the same instance across different cameras. Existing ReID methods mostly utilize alignment-based or attention-based strategies to generate effective feature representations. However, most of these methods only extract general feature by employing single input image itself, overlooking the exploration of relevance between comparing images. To fill this gap, we propose a novel end-to-end trainable dynamic convolution framework named Instance and Pair-Aware Dynamic Networks in this paper. The proposed model is composed of three main branches where a self-guided dynamic branch is constructed to strengthen instance-specific features, focusing on every single image. Furthermore, we also design a mutual-guided dynamic branch to generate pair-aware features for each pair of images to be compared. Extensive experiments are conducted in order to verify the effectiveness of our proposed algorithm. We evaluate our algorithm in several mainstream person and vehicle ReID datasets including CUHK03, DukeMTMCreID, Market-1501, VeRi776 and VehicleID. In some datasets our algorithm outperforms state-of-the-art methods and in others, our algorithm achieves a comparable performance.