Pyramidal Person Re-IDentification via Multi-Loss Dynamic Training

Abstract

Most existing Re-IDentification (Re-ID) methods are highly dependent on precise bounding boxes that enable images to be aligned with each other. However, due to the challenging practical scenarios, current detection models often produce inaccurate bounding boxes, which inevitably degenerate the performance of existing Re-ID algorithms. In this paper, we propose a novel coarse-to-fine pyramid model to relax the need of bounding boxes, which not only incorporates local and global information, but also integrates the gradual cues between them. The pyramid model is able to match at different scales and then search for the correct image of the same identity, even when the image pairs are not aligned. In addition, in order to learn discriminative identity representation, we explore a dynamic training scheme to seamlessly unify two losses and extract appropriate shared information between them. Experimental results clearly demonstrate that the proposed method achieves the state-of-the-art results on three datasets. Especially, our approach exceeds the current best method by 9.5% on the most challenging CUHK03 dataset.

Bag of Tricks and a Strong Baseline for Deep Person Re-Identification

“…All methods have been divided into different types. Pyramid [22] achieves surprising performance on two datasets. However, it concatenates 21 local features of different scale.…”

Visual Person Understanding Through Multi-task and Multi-dataset Learning

“…Even though the current top approach achieves 88.2% mAP on the Market dataset, we still outperform many recent methods by a large margin. Current top performing methods typically use a complex architecture [39,38,46] or tricks such as larger input images and more elaborate augmentations [20]. Our single-task baseline is essentially a simplified TriNet architecture [8], nevertheless, it still significantly improves the original mAP score of 69.14% by over 8%, yielding a solid baseline performance for person ReID.…”

Progressive Bilateral-Context Driven Model for Post-Processing Person Re-Identification

“…1) Market1501: In Table VI, we report the comparison results with 13 non-post-processing methods and 3 postprocessing methods. Compared with the non-post-processing methods, the proposed method surpasses all methods on mAP, and gets the second best result at Rank-1 and performs slightly worse than the Pyramid [44] by 0.1% at Rank-1. However, the proposed method is very likely to have a better performance with a better baseline.…”