Deep Reinforcement Learning of Region Proposal Networks for Object Detection

Forskningsoutput: Kapitel i bok/rapport/Conference proceedingKonferenspaper i proceedingPeer review

39 Citeringar (SciVal)

Sammanfattning

We propose drl-RPN, a deep reinforcement learning-based visual recognition model consisting of a sequential region proposal network (RPN) and an object detector. In contrast to typical RPNs, where candidate object regions (RoIs) are selected greedily via class-agnostic NMS, drl-RPN optimizes an objective closer to the final detection task. This is achieved by replacing the greedy RoI selection process with a sequential attention mechanism which is trained via deep reinforcement learning (RL). Our model is capable of accumulating class-specific evidence over time, potentially affecting subsequent proposals and classification scores, and we show that such context integration significantly boosts detection accuracy. Moreover, drl-RPN automatically decides when to stop the search process and has the benefit of being able to jointly learn the parameters of the policy and the detector, both represented as deep networks. Our model can further learn to search over a wide range of exploration-accuracy trade-offs making it possible to specify or adapt the exploration extent at test time. The resulting search trajectories are image- and category-dependent, yet rely only on a single policy over all object categories. Results on the MS COCO and PASCAL VOC challenges show that our approach outperforms established, typical state-of-the-art object detection pipelines.

Originalspråkengelska
Titel på värdpublikationProceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018
FörlagIEEE Computer Society
Sidor6945-6954
Antal sidor10
ISBN (elektroniskt)9781538664209
DOI
StatusPublished - 2018 dec. 17
Evenemang31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018 - Salt Lake City, USA
Varaktighet: 2018 juni 182018 juni 22

Konferens

Konferens31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018
Land/TerritoriumUSA
OrtSalt Lake City
Period2018/06/182018/06/22

Ämnesklassifikation (UKÄ)

  • Datorseende och robotik (autonoma system)

Fingeravtryck

Utforska forskningsämnen för ”Deep Reinforcement Learning of Region Proposal Networks for Object Detection”. Tillsammans bildar de ett unikt fingeravtryck.

Citera det här