AI Paper Atlas

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

Adaptive Multi-task Learning for Few-shot Object Detection

Yan Ren, Yanling Li, Adams Wai-Kin Kong

ECCV 2024 · Detection and segmentation › Open-set and few-shot detection · approach: Few-shot object detection · 7 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
split shared RCNN head into double-head classification/localization branches (ablation)DeFRCN baseline · COCO 10-shotmAP: 16.7 -> 17.4Improved
add precision-driven gradient balancer to double-head RCNN (ablation)Enhanced baseline · COCO 10-shotmAP: 17.4 -> 18.6Improved
use PCGrad as gradient modulation instead of the proposed balancer (ablation)Enhanced baseline · COCO 10-shotmAP: 17.4 -> 9.8Hurt
use existing closed-form gradient methods (GradVac, NashMTL) (ablation)Enhanced baseline · COCO 10-shotmAP: 17.4 -> 17.3 (GradVac), 17.2 (NashMTL)No clear effect
add CLIP knowledge distillation (ablation)Double-head + balancer · COCO 10-shotmAP: 18.4 -> 18.6Improved
add CLIP-based score refinement at inference (ablation)Full method · COCO 10-shotmAP: 18.6 -> 22.7Improved
add score refinement to the DeFRCN baseline instead of PCB (ablation)DeFRCN · COCO 10-shotmAP: 18.5 -> 19.6Improved
tune score refinement trade-off omega (ablation)Score refinement · COCO 10-shotmAP: 18.50 (no refine) -> 22.7 (omega 0.6)Improved
adaptive balancer vs grid-searched gradient ratios (ablation)Gradient balancer · COCO 10-shotgradient ratiosNo clear effect
use too small gamma_cls and gamma_reg (ablation)Gradient balancer · COCO 10-shotmAP: 0.5 (gamma 0.5) vs 18.4 (gamma 1)Hurt
add full method on cross-domain COCO to VOCDeFRCN · COCO to VOC cross-domainmAP: 41.0 -> 42.5Improved
add full method vs RISF on COCO mid-shotsFull method · COCO 3-shot and 5-shotmAP: 17.5 vs 18.2 (3-shot), 19.5 vs 20.3 (5-shot)Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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