File Download
There are no files associated with this item.
Supplementary
-
Citations:
- Appears in Collections:
Conference Paper: Sparse R-CNN: End-to-End Object Detection With Learnable Proposals
Title | Sparse R-CNN: End-to-End Object Detection With Learnable Proposals |
---|---|
Authors | |
Issue Date | 2021 |
Citation | Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Virtual Conference, 19-25 June 2021, p. 14454-14463 How to Cite? |
Abstract | We present Sparse R-CNN, a purely sparse method for object detection in images. Existing works on object detection heavily rely on dense object candidates, such as k anchor boxes pre-defined on all grids of image feature map of size H × W. In our method, however, a fixed sparse set of learned object proposals, total length of N, are provided to object recognition head to perform classification and location. By eliminating HW k (up to hundreds of thousands) hand-designed object candidates to N (e.g.
100) learnable proposals, Sparse R-CNN completely avoids all efforts related to object candidates design and many-toone label assignment. More importantly, final predictions are directly output without non-maximum suppression postprocedure. Sparse R-CNN demonstrates accuracy, run-time and training convergence performance on par with the wellestablished detector baselines on the challenging COCO
dataset, e.g., achieving 45.0 AP in standard 3× training schedule and running at 22 fps using ResNet-50 FPN model. We hope our work could inspire re-thinking the convention of dense prior in object detectors. The code is available at: https://github.com/PeizeSun/SparseR-CNN. |
Description | Paper Session Eleven: Paper ID 2829 |
Persistent Identifier | http://hdl.handle.net/10722/301313 |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Sun, P | - |
dc.contributor.author | Zhang, R | - |
dc.contributor.author | Jiang, Y | - |
dc.contributor.author | Kong, T | - |
dc.contributor.author | Xu, C | - |
dc.contributor.author | Zhan, W | - |
dc.contributor.author | Tomizuka, M | - |
dc.contributor.author | Li, L | - |
dc.contributor.author | Yuan, Z | - |
dc.contributor.author | Wang, C | - |
dc.contributor.author | Luo, P | - |
dc.date.accessioned | 2021-07-27T08:09:16Z | - |
dc.date.available | 2021-07-27T08:09:16Z | - |
dc.date.issued | 2021 | - |
dc.identifier.citation | Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Virtual Conference, 19-25 June 2021, p. 14454-14463 | - |
dc.identifier.uri | http://hdl.handle.net/10722/301313 | - |
dc.description | Paper Session Eleven: Paper ID 2829 | - |
dc.description.abstract | We present Sparse R-CNN, a purely sparse method for object detection in images. Existing works on object detection heavily rely on dense object candidates, such as k anchor boxes pre-defined on all grids of image feature map of size H × W. In our method, however, a fixed sparse set of learned object proposals, total length of N, are provided to object recognition head to perform classification and location. By eliminating HW k (up to hundreds of thousands) hand-designed object candidates to N (e.g. 100) learnable proposals, Sparse R-CNN completely avoids all efforts related to object candidates design and many-toone label assignment. More importantly, final predictions are directly output without non-maximum suppression postprocedure. Sparse R-CNN demonstrates accuracy, run-time and training convergence performance on par with the wellestablished detector baselines on the challenging COCO dataset, e.g., achieving 45.0 AP in standard 3× training schedule and running at 22 fps using ResNet-50 FPN model. We hope our work could inspire re-thinking the convention of dense prior in object detectors. The code is available at: https://github.com/PeizeSun/SparseR-CNN. | - |
dc.language | eng | - |
dc.relation.ispartof | IEEE Computer Vision and Pattern Recognition (CVPR) Proceedings | - |
dc.title | Sparse R-CNN: End-to-End Object Detection With Learnable Proposals | - |
dc.type | Conference_Paper | - |
dc.identifier.email | Luo, P: pluo@hku.hk | - |
dc.identifier.authority | Luo, P=rp02575 | - |
dc.identifier.hkuros | 323748 | - |
dc.identifier.spage | 14454 | - |
dc.identifier.epage | 14463 | - |