DiP: Learning Discriminative Implicit Parts for Person Re-Identification
This addresses the challenge of extracting more flexible and effective features for distinguishing identities in person re-identification, with incremental improvements over existing part-based methods.
The paper tackled the problem of improving person re-identification by learning discriminative implicit parts (DiPs) that are not tied to predefined body parts, achieving state-of-the-art performance on multiple benchmarks.
In person re-identification (ReID) tasks, many works explore the learning of part features to improve the performance over global image features. Existing methods explicitly extract part features by either using a hand-designed image division or keypoints obtained with external visual systems. In this work, we propose to learn Discriminative implicit Parts (DiPs) which are decoupled from explicit body parts. Therefore, DiPs can learn to extract any discriminative features that can benefit in distinguishing identities, which is beyond predefined body parts (such as accessories). Moreover, we propose a novel implicit position to give a geometric interpretation for each DiP. The implicit position can also serve as a learning signal to encourage DiPs to be more position-equivariant with the identity in the image. Lastly, an additional DiP weighting is introduced to handle the invisible or occluded situation and further improve the feature representation of DiPs. Extensive experiments show that the proposed method achieves state-of-the-art performance on multiple person ReID benchmarks.