AI Paper Atlas

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

Domain-Auxiliary Infrared Moving Small Target Detection by Learning to Overlook Domain Discrepancy

Shengjia Chen, Luping Ji, Shuang Peng, Sicheng Zhu, Mao Ye

AAAI 2026 · Detection and segmentation › Open-set and few-shot detection · approach: Domain-adaptive object detection · 1 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 target consistency contrastive learning alone (ablation)Loddis baseline · (3IR+7DA)->IRmAP50: 36.23 -> 38.17Improved
add correlation weakening alone (ablation)Loddis baseline · (3IR+7DA)->IRmAP50: 36.23 -> 37.47Improved
add domain confusing alone (ablation)Loddis baseline · (3IR+7DA)->IRmAP50: 36.23 -> 37.52Improved
add all three components (ablation)Loddis baseline · (3IR+7DA)->IRmAP50: 36.23 -> 42.30Improved
add all three components (ablation)Loddis baseline · (3DA+7IR)->DAF1: 76.44 -> 79.96Improved
add all three components (ablation)Loddis baseline · (3TS+7DA)->TSmAP50: 53.13 -> 58.66Improved
add domain confusing on top of correlation weakening and target contrastive learning (ablation)Loddis · (3DA+7IR)->DAF1: 79.53 -> 79.96Improved
add correlation weakening on top of domain confusing and target contrastive learning (ablation)Loddis · (3DA+7IR)->DAF1: 78.76 -> 79.96Improved
add domain confusing alone (ablation)Loddis baseline · (3TS+7DA)->TSmAP50: 53.13 -> 53.41No clear effect
add auxiliary domain data to training (naive mixing) for existing detectorsexisting detectors such as MSHNet · mixed-domain ISTDF1: -8.14%, -9.24%, -10.94%Hurt
apply Loddis to add auxiliary-domain databaseline detector · six mixed-domain datasetsF1Improved
use Loddis (single frame) instead of multi-frame SSTNetinfrared small target detection · (3IR+7DA)->IRF1: 62.47 -> 65.16Improved

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