Deep Representation Learning with Part Loss for Person Re-Identification
This work addresses the challenge of person re-identification for surveillance and security applications, presenting an incremental improvement over existing deep learning methods.
The paper tackles the problem of learning discriminative representations for person re-identification by addressing the tendency of deep networks to focus only on specific body parts, proposing a part loss method that enforces attention to the entire human body and achieves improved performance on datasets like Market1501, CUHK03, and VIPeR.
Learning discriminative representations for unseen person images is critical for person Re-Identification (ReID). Most of current approaches learn deep representations in classification tasks, which essentially minimize the empirical classification risk on the training set. As shown in our experiments, such representations commonly focus on several body parts discriminative to the training set, rather than the entire human body. Inspired by the structural risk minimization principle in SVM, we revise the traditional deep representation learning procedure to minimize both the empirical classification risk and the representation learning risk. The representation learning risk is evaluated by the proposed part loss, which automatically generates several parts for an image, and computes the person classification loss on each part separately. Compared with traditional global classification loss, simultaneously considering multiple part loss enforces the deep network to focus on the entire human body and learn discriminative representations for different parts. Experimental results on three datasets, i.e., Market1501, CUHK03, VIPeR, show that our representation outperforms the existing deep representations.