AI Paper Atlas

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

Remedying Target-Domain Astigmatism for Cross-Domain Few-Shot Object Detection

Yongwei Jiang, Yixiong Zou, Yuhua Li, Ruixuan Li

CVPR 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 NCM (negative context modulation) (ablation)GLIP Swin-T · 6 CD-FSOD datasets, 5-shotmAP: +1.06% avgImproved
add PPR (positive pattern refinement) (ablation)GLIP Swin-T · 6 CD-FSOD datasets, 5-shotmAP: +2.06% avgImproved
add TSA (textual semantic alignment) (ablation)GLIP Swin-T · 6 CD-FSOD datasets, 5-shotmAP: +1.59% avgImproved
add NCM, PPR and TSA together (ablation)GLIP Swin-T · DeepFish 5-shotmAP: 28.40 -> 33.87Improved
add NCM, PPR and TSA together (ablation)GLIP Swin-T · UODD 5-shotmAP: 11.40 -> 15.66Improved
apply full method to GLIP in 1-shotGLIP Swin-T · 6 datasets 1-shot avgmAP: 18.98 -> 23.81Improved
apply full method to GLIP in 10-shotGLIP Swin-T · 6 datasets 10-shot avgmAP: 33.93 -> 39.17Improved
increase background text count from 50 to 200 (ablation)TSA module · text count studyAP: 39.34 -> 42.87Improved
increase background text count from 200 to 400 (ablation)TSA module · text count studyAP: 42.87 -> 44.05No clear effect
increase GPU memory with more background texts (ablation)TSA module · text count studyGPU memory: 8762 MB -> 9245 MBHurt
set TSA loss weight to 10^3 versus extremes (ablation)TSA loss · parameter analysisdetection performanceMixed
set NCM threshold to 0.75 versus lower thresholds (ablation)NCM · parameter analysisdetection performanceMixed

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