Papers › SVDNet for Pedestrian Retrieval

SVDNet for Pedestrian Retrieval

16 Mar 2017ICCV 2017 10arXiv:1703.05693archive 2025-07-28

Yifan Sun, Liang Zheng, Weijian Deng, Shengjin Wang

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.

Paper PDF Conference PDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Person Re-Identification Representation Learning Retrieval

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Person Re-Identification	CUHK03 detected	SVDNet-ResNet50	MAP	37.3	#14 of 19	Archive leaderboard	report
Person Re-Identification	CUHK03 detected	SVDNet-ResNet50	Rank-1	41.5	#14 of 19	Archive leaderboard	report
Person Re-Identification	CUHK03 detected	SVDNet-CaffeNet	MAP	24.9	#16 of 19	Archive leaderboard	report
Person Re-Identification	CUHK03 detected	SVDNet-CaffeNet	Rank-1	27.7	#16 of 19	Archive leaderboard	report
Person Re-Identification	DukeMTMC-reID	SVDNet	Rank-1	76.7	#76 of 94	Archive leaderboard	report
Person Re-Identification	DukeMTMC-reID	SVDNet	mAP	56.8	#76 of 94	Archive leaderboard	report
Person Re-Identification	Market-1501	SVDNet	Rank-1	82.3	#109 of 135	Archive leaderboard	report
Person Re-Identification	Market-1501	SVDNet	mAP	62.1	#109 of 135	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

1x1 Convolution Average Pooling Batch Normalization Bottleneck Residual Block Convolution Global Average Pooling Kaiming Initialization Max Pooling ReLU Residual Block Residual Connection

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections