CM-NAS: Rethinking Cross-Modality Neural Architectures for Visible-Infrared Person Re-Identification

by   Chaoyou Fu, et al.

Visible-Infrared person re-identification (VI-ReID) aims at matching cross-modality pedestrian images, breaking through the limitation of single-modality person ReID in dark environment. In order to mitigate the impact of large modality discrepancy, existing works manually design various two-stream architectures to separately learn modality-specific and modality-sharable representations. Such a manual design routine, however, highly depends on massive experiments and empirical practice, which is time consuming and labor intensive. In this paper, we systematically study the manually designed architectures, and identify that appropriately splitting Batch Normalization (BN) layers to learn modality-specific representations will bring a great boost towards cross-modality matching. Based on this observation, the essential objective is to find the optimal splitting scheme for each BN layer. To this end, we propose a novel method, named Cross-Modality Neural Architecture Search (CM-NAS). It consists of a BN-oriented search space in which the standard optimization can be fulfilled subject to the cross-modality task. Besides, in order to better guide the search process, we further formulate a new Correlation Consistency based Class-specific Maximum Mean Discrepancy (C3MMD) loss. Apart from the modality discrepancy, it also concerns the similarity correlations, which have been overlooked before, in the two modalities. Resorting to these advantages, our method outperforms state-of-the-art counterparts in extensive experiments, improving the Rank-1/mAP by 6.70 code will be released soon.


page 1

page 2

page 3

page 4


Bridging the Distribution Gap of Visible-Infrared Person Re-identification with Modality Batch Normalization

Visible-infrared cross-modality person re-identification (VI-ReID), whos...

MSO: Multi-Feature Space Joint Optimization Network for RGB-Infrared Person Re-Identification

The RGB-infrared cross-modality person re-identification (ReID) task aim...

Neural Feature Search for RGB-Infrared Person Re-Identification

RGB-Infrared person re-identification (RGB-IR ReID) is a challenging cro...

Homogeneous and Heterogeneous Relational Graph for Visible-infrared Person Re-identification

Visible-infrared person re-identification (VI Re-ID) aims to match perso...

Modality-Adaptive Mixup and Invariant Decomposition for RGB-Infrared Person Re-Identification

RGB-infrared person re-identification is an emerging cross-modality re-i...

Bi-directional Exponential Angular Triplet Loss for RGB-Infrared Person Re-Identification

RGB-Infrared person re-identification (RGB-IR ReID) is a cross-modality ...

MMD-ReID: A Simple but Effective Solution for Visible-Thermal Person ReID

Learning modality invariant features is central to the problem of Visibl...