AI Paper Atlas

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

Focus on Query: Adversarial Mining Transformer for Few-Shot Segmentation

Yuan Wang, Naisong Luo, Tianzhu Zhang

NeurIPS 2023 · Detection and segmentation › Open-set and few-shot detection · approach: Few-shot segmentation · 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
Add object mining transformer G to the query-feature baseline (ablation)AMFormer · Pascal-5^i first split, ResNet-101, 1-shotmIoU: 65.0 -> 66.5Improved
Use multi-scale rather than single-scale object mining (ablation)AMFormer · Pascal-5^i first split, ResNet-101, 1-shotmIoU: 66.5 -> 69.5Improved
Add detail mining transformer D without diversity loss (ablation)AMFormer with multi-scale G · Pascal-5^i first split, ResNet-101, 1-shotmIoU: 69.5 -> 69.7Improved
Add diversity loss to detail mining transformer D (ablation)AMFormer with multi-scale G · Pascal-5^i first split, ResNet-101, 1-shotmIoU: 69.5 -> 70.7Improved
Increase local proxy count from 4 to 10 (ablation)AMFormer · Pascal-5^i first split, ResNet-101, 1-shotmIoU: 70.7 -> 71.3Improved
Increase local proxy count beyond 10 to 12 or 14 (ablation)AMFormer · Pascal-5^i first split, ResNet-101, 1-shotmIoU: 71.3 -> 71.2No clear effect
Replace mask support labels with bounding-box labels (ablation)AMFormer · Pascal-5^i first split, ResNet-101, 1-shotmIoU: 71.3 -> 70.5Hurt
Replace mask support labels with scribble labels (ablation)AMFormer · Pascal-5^i first split, ResNet-101, 1-shotmIoU: 71.3 -> 70.0Hurt
Add ensemble strategy (ablation)AMFormer · Pascal-5^i, ResNet-101, 1-shotmIoU: 69.3 -> 70.7Improved
Erode support foreground features across the tested ratios (ablation)PFENet and HDMNet · Pascal-5^i first split, ResNet-50, 1-shotmIoU: PFENet: 60.6, 61.0, 61.5, 61.2, 61.0, 61.2; HDMNet: 69.3, 70.0, 70.5, 70.4, 69.9, 70.2No clear effect
Use AMFormer instead of the strongest reported baselineFew-shot segmentation · PASCAL-5^i 1-shot, Res-101mIoU: 67.9 -> 70.7Improved
Use AMFormer instead of the strongest reported baselineFew-shot segmentation · PASCAL-5^i 5-shot, Res-50mIoU: 71.8 -> 73.2Improved

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