AI Paper Atlas

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

Segment Everything Everywhere All at Once

Xueyan Zou, Jianwei Yang, Hao Zhang, Feng Li, Linjie Li, Jianfeng Wang, Lijuan Wang, Jianfeng Gao, Yong Jae Lee

NeurIPS 2023 · Detection and segmentation › Open-set and few-shot detection · approach: Open-vocabulary semantic segmentation · 151 citations (OpenAlex)

Read the paper

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
SEEM vs SAM (B)interactive segmentation · PascalVOC20-NoC90: 4.12 -> 3.79Improved
add visual compositional prompt to textSEEM (T) · RefCOCOgcIoU: +10.5 cIoUImproved
self-attention composition instead of output ensemble (ablation)SEEM (T) · RefCOCOgcIoU: 63.0 -> 71.5Improved
visual output query instead of text output query (ablation)SEEM (T) composition · RefCOCOgcIoU: 66.5 -> 71.5Improved
add text prompt to visual prompt (ablation)SEEM (T) · RefCOCOgcIoU: 70.7 -> 71.5Improved
train from scratch instead of X-Decoder checkpoint (ablation)SEEM (T) · RefCOCOgcIoU: 58.0 -> 51.4Hurt
train from scratch (ablation)SEEM (T) · Pascal VOCNoC90: 4.67 -> 4.41Improved
increase interactive iterations 1 -> 5 (ablation)SEEM (T) · Pascal VOCNoC90: 5.14 -> 4.59Improved
use LVIS masks (ablation)SEEM (T) · Pascal VOCNoC90: 0.3 point gain on NoC@0.9Improved
more interactive iterations (ablation)SEEM (T) · COCOPQ: 50.7 -> 50.6No clear effect

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