AI Paper Atlas

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

OTSeg: Multi-prompt Sinkhorn Attention for Zero-Shot Semantic Segmentation

Kwanyoung Kim, Yujin Oh, Jong Chul Ye

ECCV 2024 · Detection and segmentation › Open-set and few-shot detection · approach: Prompted SAM segmentation · 13 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
replace cross-attention with MPSA (multi-prompt Sinkhorn attention) plus multiple text prompts (ablation)OTSeg decoder · VOC 2012 (inductive)hIoU: 77.6 -> 87.1Improved
naively add multiple text prompts to standard cross-attention (ablation)ZegCLIP-style cross-attention decoder · VOC 2012 (inductive)hIoU: 84.3 -> 77.6Hurt
naively add multiple text prompts to standard cross-attention (ablation)ZegCLIP-style cross-attention decoder · PASCAL Context (inductive)hIoU: 50.3 -> 54.5Improved
ensemble decoder output with refined score map (OTSeg+) (ablation)OTSeg · VOC 2012 (inductive)hIoU: 84.5 -> 87.1Improved
ensemble decoder output with refined score map (OTSeg+) (ablation)OTSeg · PASCAL Context (inductive)hIoU: 54.8 -> 57.7Improved
ensemble decoder output with refined score map (OTSeg+) (ablation)OTSeg · COCO-Stuff164K (fully supervised)hIoU: 50.5 -> 50.1Hurt
use MPS refined score map only instead of decoder output (ablation)OTSeg · COCO-Stuff164K (inductive)hIoU: 41.4 -> 39.3Hurt
increase number of text prompts from 6 to 8 (ablation)OTSeg+ · PASCAL Context (inductive)hIoU: 50.3 -> 57.7Improved
increase number of text prompts from 6 to 8 (ablation)OTSeg+ · VOC 2012 (inductive)hIoU: 87.1 -> 86.1Hurt
OTSeg over ZegCLIP in cross-dataset transfer from COCO-156 to PASCAL ContextOTSeg (inductive) · COCO-156 to PASCAL ContextmIoU: 41.2 -> 49.3Improved
OTSeg MPSA overhead relative to ZegCLIPOTSeg · Efficiency (3090 GPU)FPS: 25.6 -> 23.6Hurt

Later papers that compared with this method

1 later accepted paper reports OTSeg as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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