SVDNet for Pedestrian Retrieval

TL;DR

This paper introduces SVDNet, a deep learning method for person re-identification that uses Singular Vector Decomposition to orthogonalize weight vectors, resulting in more discriminative features and improved retrieval accuracy.

Contribution

The paper proposes a novel SVD-based training scheme with RRI to enforce orthogonality in CNN weights, enhancing re-ID performance.

Findings

Significant accuracy improvements on multiple datasets.

Effective reduction of correlation among projection vectors.

Enhanced discriminative power of FC descriptors.

Abstract

This paper proposes the SVDNet for retrieval problems, with focus on the application of person re-identification (re-ID). We view each weight vector within a fully connected (FC) layer in a convolutional neuron network (CNN) as a projection basis. It is observed that the weight vectors are usually highly correlated. This problem leads to correlations among entries of the FC descriptor, and compromises the retrieval performance based on the Euclidean distance. To address the problem, this paper proposes to optimize the deep representation learning process with Singular Vector Decomposition (SVD). Specifically, with the restraint and relaxation iteration (RRI) training scheme, we are able to iteratively integrate the orthogonality constraint in CNN training, yielding the so-called SVDNet. We conduct experiments on the Market-1501, CUHK03, and Duke datasets, and show that RRI effectively reduces the correlation among the projection vectors, produces more discriminative FC descriptors, and significantly improves the re-ID accuracy. On the Market-1501 dataset, for instance, rank-1 accuracy is improved from 55.3% to 80.5% for CaffeNet, and from 73.8% to 82.3% for ResNet-50.