SVDNet for Pedestrian Retrieval
This work addresses the specific problem of person re-identification for surveillance and security applications, representing an incremental improvement by optimizing deep representation learning with orthogonality constraints.
The paper tackled the problem of correlated weight vectors in fully connected layers of CNNs compromising pedestrian retrieval performance by proposing SVDNet, which integrates orthogonality constraints via Singular Vector Decomposition and a restraint and relaxation iteration training scheme, resulting in significant accuracy improvements, such as rank-1 accuracy increasing from 55.3% to 80.5% for CaffeNet on the Market-1501 dataset.
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.