AlignedReID: Surpassing Human-Level Performance in Person Re-Identification
This work addresses person re-identification for surveillance and security applications, representing a significant advance by exceeding human-level accuracy on standard benchmarks.
The paper tackled person re-identification by proposing AlignedReID, a method that jointly learns global and local features without extra supervision, achieving rank-1 accuracies of 94.4% on Market1501 and 97.8% on CUHK03, surpassing state-of-the-art and human-level performance.
In this paper, we propose a novel method called AlignedReID that extracts a global feature which is jointly learned with local features. Global feature learning benefits greatly from local feature learning, which performs an alignment/matching by calculating the shortest path between two sets of local features, without requiring extra supervision. After the joint learning, we only keep the global feature to compute the similarities between images. Our method achieves rank-1 accuracy of 94.4% on Market1501 and 97.8% on CUHK03, outperforming state-of-the-art methods by a large margin. We also evaluate human-level performance and demonstrate that our method is the first to surpass human-level performance on Market1501 and CUHK03, two widely used Person ReID datasets.