AI Paper Atlas

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

Language-driven Semantic Segmentation

Boyi Li, Kilian Q Weinberger, Serge Belongie, Vladlen Koltun, Rene Ranftl

ICLR 2022 · Detection and segmentation › Open-set and few-shot detection · approach: Few-shot segmentation · 161 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
Use LSeg instead of ZS3Net with ResNet101Zero-shot semantic segmentation · PASCAL-5imIoU: 38.3 -> 47.4Improved
Use LSeg instead of ZS3Net with ResNet101Zero-shot semantic segmentation · COCO-20imIoU: 21.1 -> 23.4Improved
Use LSeg with ViT-L/16 instead of HSNet with ResNet101Semantic segmentation · FSS-1000mIoU: 86.5 -> 87.8Improved
Use LSeg with ResNet101 instead of HSNet with ResNet101Semantic segmentation · FSS-1000mIoU: 86.5 -> 84.7Hurt
Add two DepthwiseBlocks rather than using none (ablation)LSeg · ADE20KmIoU: 37.83 -> 39.45Improved
Add two BottleneckBlocks rather than using none (ablation)LSeg · ADE20KmIoU: 37.83 -> 39.79Improved
Use four DepthwiseBlocks rather than two (ablation)LSeg · ADE20KmIoU: 39.45 -> 0.18Hurt
Use four BottleneckBlocks rather than two (ablation)LSeg · ADE20KmIoU: 39.79 -> 38.78Hurt
Replace CLIP ViT-B/32 text encoder with CLIP RN50x16 (ablation)LSeg with ViT-B/32 image encoder · ADE20KmIoU: 37.83 -> 40.36Improved
Replace CLIP ViT-B/32 text encoder with CLIP ViT-B/16 (ablation)LSeg with ViT-B/32 image encoder · ADE20KmIoU: 37.83 -> 38.69Improved
Replace CLIP ViT-B/32 text encoder with CLIP RN50x4 (ablation)LSeg with ViT-B/32 image encoder · ADE20KmIoU: 37.83 -> 38.93Improved
Use RN50x16 rather than ViT-B/32 text encoder on the fixed label set (ablation)LSeg with ViT-L/16 image encoder · ADE20K validationmIoU: 46.28 -> 47.25Improved

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