Neural Feature Search For Rgb-infrared Person Re-identification
2021 · Yehansen Chen, Lin Wan, Zhihang Li, et al.
Abstract
RGB-Infrared person re-identification (RGB-IR ReID) is a challenging cross-modality retrieval problem, which aims at matching the person-of-interest over visible and infrared camera views. Most existing works achieve performance gains through manually-designed feature selection modules, which often require significant domain knowledge and rich experience. In this paper, we study a general paradigm, termed Neural Feature Search (NFS), to automate the process of feature selection. Specifically, NFS combines a dual-level feature search space and a differentiable search strategy to jointly select identity-related cues in coarse-grained channels and fine-grained spatial pixels. This combination allows NFS to adaptively filter background noises and concentrate on informative parts of human bodies in a data-driven manner. Moreover, a cross-modality contrastive optimization scheme further guides NFS to search features that can minimize modality discrepancy whilst maximizing inter-class distanc
Authors
(none)
Tags
Stats
Related papers
- A Similarity Inference Metric For Rgb-infrared Cross-modality Person Re-identification (2020)12.99
- Learning Modal-invariant And Temporal-memory For Video-based Visible-infrared Person Re-identification (2022)14.23
- Auto-reid: Searching For A Part-aware Convnet For Person Re-identification (2019)17.27
- Mutual Information Guided Optimal Transport For Unsupervised Visible-infrared Person Re-identification (2024)0.00
- Implicit Discriminative Knowledge Learning For Visible-infrared Person Re-identification (2024)16.19
- BIT: Matching-based Bi-directional Interaction Transformation Network For Visible-infrared Person Re-identification (2026)0.00
- Advancing Person Re-identification: Tensor-based Feature Fusion And Multilinear Subspace Learning (2023)2.26
- Adaptive Re-ranking Of Deep Feature For Person Re-identification (2018)0.00