Camera Bias Regularization for Person Re-identification
Person re-identification (Re-ID) is to match persons captured by non-overlapping cameras. Due to the discrepancies between cameras caused by illumination, background, or viewpoint, the underlying difficulty for Re-ID is the camera bias problem, which leads to the large gap of within-identity features from different cameras. With limited cross-camera annotated data, Re-ID models tend to learn camera-related features, instead of identity-related features. Consequently, Re-ID models suffer from poor transfer ability from seen domains to unseen domains. In this paper, we investigate the camera bias problem in supervised learning, unsupervised learning, and their variants. In particular, we propose a novel Camera Bias Regularization (CBR) term to reduce the feature distribution gap between cameras by enlarging the intra-camera distance and reducing the inter-camera distance simultaneously. Extensive experiments on person Re-ID tasks validate the effectiveness and universality of the proposed CBR.
PDF Abstract
Market-1501
DukeMTMC-reID
