Beyond Triplet Loss: Person Re-identification with Fine-grained Difference-aware Pairwise Loss
This work improves person re-identification for surveillance and security applications by enabling more accurate differentiation of similar identities, though it is incremental as it builds upon existing loss function methods.
The paper tackles the problem of person re-identification by addressing the limitation of triplet loss in learning fine-grained appearance differences, introducing a novel pairwise loss that adaptively penalizes small and large differences, resulting in substantial performance improvements on four benchmark datasets and enhanced data efficiency.
Person Re-IDentification (ReID) aims at re-identifying persons from different viewpoints across multiple cameras. Capturing the fine-grained appearance differences is often the key to accurate person ReID, because many identities can be differentiated only when looking into these fine-grained differences. However, most state-of-the-art person ReID approaches, typically driven by a triplet loss, fail to effectively learn the fine-grained features as they are focused more on differentiating large appearance differences. To address this issue, we introduce a novel pairwise loss function that enables ReID models to learn the fine-grained features by adaptively enforcing an exponential penalization on the images of small differences and a bounded penalization on the images of large differences. The proposed loss is generic and can be used as a plugin to replace the triplet loss to significantly enhance different types of state-of-the-art approaches. Experimental results on four benchmark datasets show that the proposed loss substantially outperforms a number of popular loss functions by large margins; and it also enables significantly improved data efficiency.