AI Paper Atlas

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

AMP: Adaptive Masked Proxies for Few-Shot Segmentation

Mennatullah Siam, Boris N. Oreshkin, Martin Jagersand

ICCV 2019 · Detection and segmentation › Open-set and few-shot detection · approach: Few-shot segmentation · 236 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 proxy adaptation (alpha > 0) (ablation)AMP imprinting · PASCAL-5i fold 0 (1-shot)mIoU: 13.6 -> 41.9Improved
add multi-resolution imprinting (ablation)AMP imprinting · PASCAL-5i fold 0 (1-shot)mIoU: 34.8 -> 41.9Improved
imprint weights with masked proxies instead of fine-tuning random weights (ablation)AMP · PASCAL-5i fold 0 (5-shot)mIoU: 28.7 -> 40.3Improved
add fine-tuning after imprinting (ablation)AMP · PASCAL-5i fold 0 (5-shot)mIoU: 40.3 -> 41.8Improved
add 2 fine-tuning iterationsAMP-2 · PASCAL-5i 5-shot (mean)mIoU: 46.4 -> 46.9Improved
add 2 fine-tuning iterationsAMP-2 · PASCAL-5i 1-shot (FG/BG protocol)mIoU: 61.9 -> 62.2Improved
add 2 fine-tuning iterationsAMP-2 · PASCAL-5i 5-shot (FG/BG protocol)mIoU: 62.1 -> 63.8Improved
use Reduced-DFCN8s backbone instead of DFCN8sAMP · PASCAL-5i 1-shot (mean)mIoU: 42.4 -> 43.4Improved
replace OSLSM two-branch method with AMP-2few-shot segmentation · PASCAL-5i 1-shot (mean)mIoU: 40.8 -> 43.4Improved
imprinted weights instead of fine-tuning in continual settingAMP · iPASCALmIoUImproved
self-adaptation with AMP plus CRF on 2-stream networkvideo object segmentation · DAVIS'16J mean: 77.2 -> 78.9Improved
self-adaptation with AMPvideo object segmentation · FBMS testF-measure: 79.0 -> 79.0No clear effect

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