A Tale of Two Losses: Discriminative Deep Feature Learning for Person Re-Identification
Lists
Only you see this
Abstract
The changing camera viewpoint on full-body pedestrians in a multi-camera scenario may be problematic to handle, above all if the fields of view are non-overlapping. A direct effect of the viewpoint variability is that a pair of images of the same person shot by different cameras may appear to be more distant from each other in the feature space than one of them from an image of a different identity captured by the same camera. In order to tackle this problem, we propose to train a state-of-the-art CNN by two new loss functions that jointly increase the inter-class discriminative power of the deep features and their intra-class compactness. In particular, one loss function promotes the aggregation of the feature points around the centres of the view they belong to, within the scope of their own identity. The second loss encourages to push away from each other the feature clusters corresponding simultaneously to different views and different identities. Under the supervision of the two new objectives we achieve state-of-the-art accuracy with ResNet50 on Market-1501 and CUHK03 datasets, beating the performance of the softmax loss.
BibTeX
@inproceedings{borgia2017tale,
author = {Alessandro Borgia and Hua Yang and Neil M. Robertson},
title = {{A Tale of Two Losses: Discriminative Deep Feature Learning for Person Re-Identification}},
booktitle = {Research},
year = {2017},
}Loading related content...