AI Paper Atlas

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

AgMTR: Agent Mining Transformer for Few-Shot Segmentation in Remote Sensing

Hanbo Bi, Yingchao Feng, Yongqiang Mao, Jianning Pei, Wenhui Diao, Hongqi Wang, Xian Sun

IJCV 2024 · Detection and segmentation › Open-set and few-shot detection · approach: Few-shot segmentation · 24 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 Agent Learning Encoder (ALE) to baseline (ablation)AgMTR baseline (DeiT-B/16) · iSAID 1-shotmIoU: 46.82 -> 48.94Improved
add Agent Aggregation Decoder (AAD) on top of ALE (ablation)AgMTR · iSAID 1-shotmIoU: 48.94 -> 50.01Improved
add Semantic Alignment Decoder (SAD) on top of ALE (ablation)AgMTR · iSAID 1-shotmIoU: 48.94 -> 50.27Improved
add SAD on top of ALE+AAD (ablation)AgMTR · iSAID 1-shotmIoU: 50.01 -> 51.58Improved
add all three components to baseline (ablation)AgMTR · iSAID 1-shotmIoU: 46.82 -> 51.58Improved
add support-prototype initialization of agents (ablation)AgMTR ALE · iSAID 1-shotmIoU: 49.12 -> 51.58Improved
add optimal transport local masks (ablation)AgMTR ALE · iSAID 1-shotmIoU: 50.74 -> 51.58Improved
add GAT in SAD (ablation)AgMTR SAD · iSAID 1-shotmIoU: 50.89 -> 51.58Improved
increase unlabeled images from 0 to 5 (ablation)AgMTR AAD · iSAID 1-shotmIoU: 50.27 -> 51.58Improved
increase unlabeled images from 5 to 9 (ablation)AgMTR AAD · iSAID 1-shotmIoU: 51.58 -> 51.61No clear effect
use 1 unlabeled image instead of 5 (ablation)AgMTR AAD · iSAID 1-shotmIoU: 50.64 -> 51.58Improved
add all agents' semantic sources (support, unlabeled, query) (ablation)AgMTR · iSAID (cosine distance)cosine distance to query prototype: 0.5843 -> 0.7465Improved

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