Sparse R-CNN: End-to-End Object Detection with Learnable Proposals

by   Peize Sun, et al.

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 HWk (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-to-one label assignment. More importantly, final predictions are directly output without non-maximum suppression post-procedure. Sparse R-CNN demonstrates accuracy, run-time and training convergence performance on par with the well-established detector baselines on the challenging COCO dataset, e.g., achieving 44.5 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:


SparseDet: Towards End-to-End 3D Object Detection

In this paper, we propose SparseDet for end-to-end 3D object detection f...

End-to-End Object Detection with Transformers

We present a new method that views object detection as a direct set pred...

SparsePoint: Fully End-to-End Sparse 3D Object Detector

Object detectors based on sparse object proposals have recently been pro...

Quasi-Dense Instance Similarity Learning

Similarity metrics for instances have drawn much attention, due to their...

Dynamic Sparse R-CNN

Sparse R-CNN is a recent strong object detection baseline by set predict...

Should All Proposals be Treated Equally in Object Detection?

The complexity-precision trade-off of an object detector is a critical p...

Sparse DETR: Efficient End-to-End Object Detection with Learnable Sparsity

DETR is the first end-to-end object detector using a transformer encoder...

Code Repositories


End-to-End Object Detection with Learnable Proposal

view repo