Sampling Agnostic Feature Representation for Long-Term Person Re-identification
arXiv:2209.09574 · doi:10.1109/TIP.2022.3207024
Abstract
Person re-identification is a problem of identifying individuals across non-overlapping cameras. Although remarkable progress has been made in the re-identification problem, it is still a challenging problem due to appearance variations of the same person as well as other people of similar appearance. Some prior works solved the issues by separating features of positive samples from features of negative ones. However, the performances of existing models considerably depend on the characteristics and statistics of the samples used for training. Thus, we propose a novel framework named sampling independent robust feature representation network (SirNet) that learns disentangled feature embedding from randomly chosen samples. A carefully designed sampling independent maximum discrepancy loss is introduced to model samples of the same person as a cluster. As a result, the proposed framework can generate additional hard negatives/positives using the learned features, which results in better discriminability from other identities. Extensive experimental results on large-scale benchmark datasets verify that the proposed model is more effective than prior state-of-the-art models.
arXiv comment11 pages, 7 figures, In IEEE Transactions on Image Processing 2022
References in corpus (8)
- Adam: A Method for Stochastic Optimization
- FaceNet: A Unified Embedding for Face Recognition and Clustering
- In Defense of the Triplet Loss for Person Re-Identification
- Learning Discriminative Features with Multiple Granularities for Person Re-Identification
- Person Re-identification: Past, Present and Future
- Bit-Scalable Deep Hashing with Regularized Similarity Learning for Image Retrieval and Person Re-identification
- Person Re-identification by Contour Sketch under Moderate Clothing Change
- The Devil is in the Middle: Exploiting Mid-level Representations for Cross-Domain Instance Matching