AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Adapting In-Domain Few-Shot Segmentation to New Domains without Source Domain Retraining

Qi Fan, Kaiqi Liu, Nian Liu, Hisham Cholakkal, Rao Muhammad Anwer, Wenbin Li, Yang Gao

ICCV 2025 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Domain-generalized segmentation · 10 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 informative structure adaptation (ISA) on top of a well-trained in-domain FSS modelSSP ResNet-50 · CD-FSS 4 datasets (5-shot avg)mIoU: 63.0 -> 70.3Improved
add ISA to PANet, FPTrans, PerSAM and DR-Adaptervarious FSS and CD-FSS models · CD-FSS 4 datasets (5-shot avg)mIoU: +6.4 to +7.3 (DR-Adapter +5.5)Improved
add model structure adaptation baseline (ablation)SSP ResNet-50 · CD-FSS 4 datasets (5-shot avg)mIoU: 63.0 -> 64.6Improved
add informative structure identification (ISI) (ablation)MSA SSP · CD-FSS 4 datasets (5-shot avg)mIoU: 64.6 -> 66.5Improved
add progressive structure adaptation (PSA) (ablation)MSA SSP · CD-FSS 4 datasets (5-shot avg)mIoU: 64.6 -> 67.6Improved
add ISI on top of MSA + PSA (ablation)ISA · DeepglobemIoU: 53.2 -> 52.7Mixed
select trainable layers with ISI instead of training only the last conv layer (ablation)ISA · CD-FSS 4 datasets (5-shot avg)mIoU: 67.6 -> 70.3Improved
use largest structure Fisher score per layer instead of the mean (ablation)ISI · CD-FSS 4 datasets (5-shot avg)mIoU: 67.8 -> 70.3Improved
increase ISI trainable layers from 1 to 3 (ablation)ISI · CD-FSS 4 datasets (5-shot avg)mIoU: 70.3 -> 71.0No clear effect
use progressive training 1->2->3->4 instead of directly training with 4-shot samples (ablation)PSA · CD-FSS 4 datasets (5-shot avg)mIoU: 67.8 -> 70.3Improved
increase support shots from 5 to 30 (ablation)ISA vs SSP baseline · CD-FSS 4 datasetsmIoU: 70.3 -> 74.6 (baseline 63.0 -> 65.2)Improved

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