AI Paper Atlas

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

Unifying Visual Perception by Dispersible Points Learning

Jianming Liang, Guanglu Song, Biao Leng, Yu Liu

ECCV 2022 · Detection and segmentation › Open-set and few-shot detection · approach: Object-level representation learning · 3 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 UniHead instead of extra blocks (ablation)ResNet-50 · ImageNet-1k valtop-1 accuracy: 79.0 -> 79.5Improved
add extra blocks to Swin-B (ablation)Swin-B · ImageNet-1k valtop-1 accuracy: 83.5 -> 83.6No clear effect
add UniHead (ablation)Swin-B · ImageNet-1k valtop-1 accuracy: 83.5 -> 83.9Improved
add task token (ablation)UniHead Faster RCNN · COCO val detectionAP: 41.6 -> 41.8Improved
add task token (ablation)UniHead Faster RCNN · COCO val keypointsAP: 50.4 -> 50.7Improved
add task-specific bias initialization (ablation)UniHead · COCO val detectionAP: 40.9 -> 41.6Improved
add task-specific bias initialization (ablation)UniHead · COCO val keypointsAP: 57.0 -> 57.9Improved
increase point number K from 8 to 16 (ablation)UniHead · COCO val detectionAP: 40.8 -> 41.8Improved
increase point number K from 16 to 32 (ablation)UniHead · COCO val detectionAP: 41.8 -> 41.5Hurt
increase transformer blocks from 1+1 to 4+4 (ablation)UniHead · COCO val detectionAP: 41.6 -> 42.0Improved
add head disentanglement (ablation)Faster RCNN · COCO val detectionAP: 38.8 -> 39.3Improved
add multi-head self attention (ablation)Faster RCNN with head disentanglement · COCO val detectionAP: 39.3 -> 39.9Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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