Skip to content

Latest commit

 

History

History
53 lines (40 loc) · 4.16 KB

sparse_rcnn.md

File metadata and controls

53 lines (40 loc) · 4.16 KB
Raw

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

November 2020

tl;dr: Sparse proposal and iterative refinement for a two-stage end-to-end object detector.

Overall impression

This paper rethinks the necessity of dense priors (either anchor boxes or reference points) in object detection, very similar to TSP. Sparse RCNN uses a number of sparse proposals (N << HWk dense priors) for object detection.

There are several papers on improving the training speed of DETR.

The iterative head design is quite inefficient in capturing the context and relationship with other parts of the image, and thus needs quite a few iterations (~6 cascaded stage). In comparison, the sparse cross attention in Deformable DETR and TSP may be a better way to go.

The authors also wrote OneNet which is a single-stage easy-to-deploy end to end object detection model.

Key ideas

  • Sparse-in and sparse out
    • DETR uses sparse set of object queries to interact with global (dense) image feature. It is also dense-to-sparse.
    • Sparse RCNN proposes both sparse proposals and sparse features
      • Sparse RCNN uses only 100 proposals, same as DETR. 300 proposal adds very little inference cost due to light design of dynamic head.
    • Sparse Proposal feature: High dim (256-d) latent features encoding pose and shape of instances. Proposal feature generates a series of customized parameters for its exclusive object recognition head via dynamic conv.
  • Three Input:
    • Image
    • A set of learned proposal boxes (fixed, and dataset independent, and may not be symmetric or shift-equivariant) --> This looks to be an inefficiency that can be optimized. Maybe something like the FoI in TSP-FCOS.
    • A set of learnable proposal features. The initial values of the proposal feature is actually not that important, given the auto-regressive iterative refinement scheme (similar to IterDet).
  • Dynamic instance interactive head --> More like a trick and an afterthought rather than intuition inspired design.
    • The interaction between Proposal feature and RoI features is modeled by a dynamic convolution. The parameters are generate by the proposal features.
    • Newly generated object boxes and object features of the next stage in iterative process. Features need to be RoI aligned again, similar to Cascade RCNN CVPR 2018. This only introduces a marginal computational overhead as the dynamic conv is very light.

Technical details

  • Set prediction loss exactly the same as DETR.
  • Ablation studies
  • The paper has a very clear evolution path of model, in Table 2, 3 and 4. According to the author's reply on Zhihu知乎.

  • 18.5到20.5：加上cascade r-cnn那样的结构

  • 20.5到32.2: cascade结构 + 上一个stage的obj feature concat到下一个stage的obj feature

  • 32.2到37.2: cascade结构 + 上一个stage的obj feature先self-att，再concat到下一个stage的obj feature

  • 37.2到42.3: cascade结构 + 上一个stage的obj feature先self-att，在作为proposal feature与下一个stage的RoI做instace interaction

  • Initialization of proposal box does not matter much

  • Number of proposals from 100 to 500 improves performance, but also requires longer training time

  • Stage increase saturates around stage 6. The iterative heads gradually refines box and removes duplicate ones.

Notes

  • Code on github
  • The Sparse RCNN paper is not very well written. Luckily the first author clarified most of the important details in Zhihu知乎.
  • The proposal can be seen as an averaged GT distribution. This should be improved to be data dependent, and the authors are working on a v2 of Sparse RCNN. The authors also argue that a reasonable statistic can already be qualified candidates. Maybe this is similar to the FoI classifier in TSP-FCOS.