CVMar 31, 2023

Adaptive Sparse Pairwise Loss for Object Re-Identification

arXiv:2303.18247v167 citationsh-index: 19Has Code
Originality Incremental advance
AI Analysis

This addresses training inefficiencies in object re-identification for computer vision applications, but is incremental as it builds on existing pairwise loss methods.

The paper tackles the problem of harmful positive pairs in object re-identification by proposing a Sparse Pairwise loss that uses few appropriate pairs per class, and shows it achieves state-of-the-art performance on multiple benchmarks.

Object re-identification (ReID) aims to find instances with the same identity as the given probe from a large gallery. Pairwise losses play an important role in training a strong ReID network. Existing pairwise losses densely exploit each instance as an anchor and sample its triplets in a mini-batch. This dense sampling mechanism inevitably introduces positive pairs that share few visual similarities, which can be harmful to the training. To address this problem, we propose a novel loss paradigm termed Sparse Pairwise (SP) loss that only leverages few appropriate pairs for each class in a mini-batch, and empirically demonstrate that it is sufficient for the ReID tasks. Based on the proposed loss framework, we propose an adaptive positive mining strategy that can dynamically adapt to diverse intra-class variations. Extensive experiments show that SP loss and its adaptive variant AdaSP loss outperform other pairwise losses, and achieve state-of-the-art performance across several ReID benchmarks. Code is available at https://github.com/Astaxanthin/AdaSP.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes