AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Cornerformer: Purifying Instances for Corner-Based Detectors

Haoran Wei, Xin Chen, Lingxi Xie, Qi Tian

ECCV 2022 · Detection and segmentation › Open-set and few-shot detection · approach: Unsupervised object and part discovery · 4 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
replace corner pooling with CTE (ablation)CornerNet · COCO val2017 (CornerNet)AP (%): 39.1 -> 40.8Improved
replace Soft-NMS with A3-NMS (ablation)CornerNet with CTE · COCO val2017 (CornerNet)AP (%): 40.8 -> 41.3Improved
replace Soft-NMS with A3-NMS (ablation)CornerNet with CTE · Citypersons valAP50 (%): 40.3 -> 45.4Improved
add full Cornerformer (CTE + A3-NMS) (ablation)CornerNet · COCO val2017AP (%): 36.9 -> 41.3Improved
add CornerformerCornerNet · COCO test-devAP (%): 40.5 -> 42.6Improved
add CornerformerCenterNet · COCO test-devAP (%): 44.9 -> 46.1Improved
add Cornerformer with pull-push branchCentripetalNet · COCO test-devAP (%): 46.1 -> 47.1Improved
use two separate CTEs for the two corner typesCornerNet with Cornerformer · COCO test-devAP (%): 42.6 -> 43.5Improved
replace corner pooling with CTE (faster speed)CornerNet · COCO test-devFPS: 4.1 -> 7.4Improved
add positional encoding to criss-cross attention (PCCA) (ablation)CTE · COCO val2017 (CornerNet)AP (%): 39.3 -> 40.1Improved
add output positional encoding PE (ablation)CTE with PCCA · COCO val2017 (CornerNet)AP (%): 40.1 -> 40.8Improved
use 4 CTE blocks instead of 3 (ablation)CornerNet w/ CTE · COCO val2017 (CornerNet)AP (%): 40.8 -> 40.4Hurt

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