Unsupervised Attention Based Instance Discriminative Learning for Person Re-Identification
This addresses the need for robust unsupervised methods in person re-identification to handle large intra-class variations without laborious data curation.
The paper tackles the problem of unsupervised person re-identification by proposing a framework that uses a novel attention mechanism with group convolutions to enhance spatial attention and reduce parameters by 59.6%, achieving state-of-the-art performance on datasets like Market1501 and DukeMTMC-reID.
Recent advances in person re-identification have demonstrated enhanced discriminability, especially with supervised learning or transfer learning. However, since the data requirements---including the degree of data curations---are becoming increasingly complex and laborious, there is a critical need for unsupervised methods that are robust to large intra-class variations, such as changes in perspective, illumination, articulated motion, resolution, etc. Therefore, we propose an unsupervised framework for person re-identification which is trained in an end-to-end manner without any pre-training. Our proposed framework leverages a new attention mechanism that combines group convolutions to (1) enhance spatial attention at multiple scales and (2) reduce the number of trainable parameters by 59.6%. Additionally, our framework jointly optimizes the network with agglomerative clustering and instance learning to tackle hard samples. We perform extensive analysis using the Market1501 and DukeMTMC-reID datasets to demonstrate that our method consistently outperforms the state-of-the-art methods (with and without pre-trained weights).