Abstract
As an instance-level recognition problem, person re-identification (ReID) relies on discriminative features, which not only capture different spatial scales but also encapsulate an arbitrary combination of multiple scales. We callse features of both homogeneous and heterogeneous scales omni-scale features. In this paper, a novel deep ReID CNN is designed, termed Omni-Scale Network (OSNet), for omni-scale feature learning. This is achieved by designing a residual block composed of multiple convolutional feature streams, each detecting features at a certain scale. Importantly, a novel unified aggregation gate is introduced to dynamically fuse multi-scale features with input-dependent channel-wise weights. To efficiently learn spatial-channel correlations and avoid overfitting, the building block uses both pointwise and depthwise convolutions. By stacking such blocks layer-by-layer, our OSNet is extremely lightweight and can be trained from scratch on existing ReID benchmarks. Despite its small model size, our OSNet achieves state-of-the-art performance on six person-ReID datasets. Code and models are available at: Https://github.com/KaiyangZhou/deep-person-reid.
Original language | English |
---|---|
Title of host publication | Proceedings - 2019 IEEE/CVF International Conference on Computer Vision, ICCV 2019 |
Publisher | IEEE |
Pages | 3701-3711 |
Number of pages | 11 |
ISBN (Electronic) | 9781728148038 |
ISBN (Print) | 9781728148045 |
DOIs | |
Publication status | Published - Oct 2019 |
Externally published | Yes |
Event | 17th IEEE/CVF International Conference on Computer Vision, ICCV 2019 - Seoul, Korea, Republic of Duration: 27 Oct 2019 → 2 Nov 2019 https://ieeexplore.ieee.org/xpl/conhome/8972782/proceeding |
Publication series
Name | Proceedings of the IEEE International Conference on Computer Vision |
---|---|
Volume | 2019-October |
ISSN (Print) | 1550-5499 |
ISSN (Electronic) | 2380-7504 |
Conference
Conference | 17th IEEE/CVF International Conference on Computer Vision, ICCV 2019 |
---|---|
Country/Territory | Korea, Republic of |
City | Seoul |
Period | 27/10/19 → 2/11/19 |
Internet address |
Scopus Subject Areas
- Software
- Computer Vision and Pattern Recognition