AI Paper Atlas

Research map / Detection and segmentation / CNN features

Context Refinement for Object Detection

Zhe Chen, Shaoli Huang, Dacheng Tao

ECCV 2018 · Detection and segmentation › CNN features · approach: Region-based and query-based detectors · 123 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add context refinement to the RPN (C-RPN) (ablation)FRCNN† · VOC 07 testAP@0.5: 0.796 -> 0.804Improved
add context refinement to the RPN (C-RPN) (ablation)FRCNN† · VOC 07 testAP@0.8: 0.442 -> 0.469Improved
add context refinement to the final refinement stage (ablation)FRCNN† with C-RPN · VOC 07 testAP@0.5: 0.804 -> 0.822Improved
add context refinement to the final refinement stage (ablation)FRCNN† with C-RPN · VOC 07 testAP@0.7: 0.650 -> 0.685Improved
add context refinement to Faster RCNNFRCNN† VGG · VOC 07 testmAP: 75.3 -> 77.6Improved
add context refinement to Faster RCNNFRCNN† Res101 · VOC 07 testmAP: 79.6 -> 82.2Improved
add context refinement to Faster RCNNFRCNN† Res101 · MS COCO test-devAP: 37.5 -> 39.0Improved
add context refinement to Deformable R-FCNDRFCN Res101 · MS COCO test-devAP: 37.1 -> 39.1Improved
add context refinement to Mask RCNNMask RCNN Res101 · MS COCO test-devAP: 40.2 -> 42.0Improved
add context refinement to Mask RCNNMask RCNN Res101 · MS COCO test-devmAP@0.7: 43.9 -> 46.4Improved
add context refinement to Faster RCNNFRCNN† Res101 · MS COCO test-devmAP(large): 51.1 -> 53.0Improved
add context refinement to Faster RCNN (Res101)FRCNN† Res101 · MS COCO test-devmAP(small): 18.8 -> 19.4Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy