AI Paper Atlas

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

Cross-Domain Few-Shot Semantic Segmentation

Shuo Lei, Xuchao Zhang, Jianfeng He, Fanglan Chen, Bowen Du, Chang-Tien Lu

ECCV 2022 · Detection and segmentation › Open-set and few-shot detection · approach: Few-shot segmentation · 78 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 pyramid anchor layers (PATM) for feature transformation (ablation)PATNet (Res-50) · CD-FSS average, 1-shotmIoU (%): 47.57 -> 56.06Improved
add pyramid anchor layers (PATM) for feature transformation (ablation)PATNet (Res-50) · CD-FSS average, 5-shotmIoU (%): 51.38 -> 61.99Improved
share one anchor layer per feature dimension instead of one per feature map (ablation)PATNet (Res-50) · CD-FSS average, 1-shotmIoU (%): 54.16 -> 56.06Improved
share one anchor layer per feature dimension instead of one per feature map (ablation)PATNet (Res-50) · CD-FSS average, 5-shotmIoU (%): 59.38 -> 61.99Improved
fine-tune low-level anchor layer at test time (TFI) (ablation)PATNet (Res-50) · Deepglobe, 1-shotmIoU (%): 35.10 -> 37.89Improved
fine-tune low-level anchor layer at test time (TFI) (ablation)PATNet (Res-50) · Deepglobe, 5-shotmIoU (%): 40.72 -> 42.97Improved
fine-tune high-level anchor layer at test time (ablation)PATNet (Res-50) · Deepglobe, 1-shotmIoU (%): 35.10 -> 37.52Improved
fine-tune medium-level anchor layer at test time (ablation)PATNet (Res-50) · Deepglobe, 1-shotmIoU (%): 35.10 -> 34.56Hurt
fine-tune medium-level anchor layer at test time (ablation)PATNet (Res-50) · Deepglobe, 5-shotmIoU (%): 40.72 -> 39.74Hurt
use PATNet with Res-50 instead of HSNetfew-shot segmentation · CD-FSS average, 1-shotmIoU (%): 47.57 -> 56.06Improved
use PATNet instead of HSNet on Chest X-rayfew-shot segmentation · Chest X-ray, 1-shotmIoU (%): 51.88 -> 66.61Improved
meta-learned few-shot methods versus linear classifier on frozen Deeplab under large domain gapHSNet vs LinearDeeplab · Deepglobe, 5-shotmIoU (%): 35.08 vs 39.69Mixed

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