AI Paper Atlas

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

X-SAM: From Segment Anything to Any Segmentation

Hao Wang, Limeng Qiao, Zequn Jie, Zhijian Huang, Chengjian Feng, Qingfang Zheng, Lin Ma, Xiangyuan Lan, Xiaodan Liang

AAAI 2026 · Detection and segmentation › Open-set and few-shot detection · approach: Interactive and referring segmentation · 29 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 mixed co-training across tasks (ablation)X-SAM · A150-OVPQ: 16.4 -> 22.4Improved
add mixed co-training across tasks (ablation)X-SAM · Reason-ValgIoU: 48.2 -> 57.1Improved
add mixed co-training across tasks (ablation)X-SAM · COCO-PanPQ: 55.3 -> 54.5Hurt
add SAM segmentation encoder next to ViT (ablation)X-SAM · GCG-ValmIoU: 64.8 -> 69.4Improved
add Swin (M2F-init) segmentation encoder next to ViT (ablation)X-SAM · GCG-ValmIoU: 64.8 -> 62.5Hurt
add Swin (M2F-init) segmentation encoder next to ViT (ablation)X-SAM · COCO-VGDAP: 40.7 -> 48.6Improved
add stage 1 segmentor fine-tuning (ablation)X-SAM · COCO-PanPQ: 45.2 -> 54.5Improved
add stage 2 alignment pre-training (ablation)X-SAM · GCG-ValmIoU: 65.4 -> 69.4Improved
add stage 2 alignment pre-training (ablation)X-SAM · COCO-PanPQ: 54.5 -> 54.7No clear effect
replace SAM decoder with Mask2Former decoder (ablation)X-SAM · segmentor fine-tuning (12 epochs)PQ: 40.9 -> 50.1Improved
use convolution connector instead of MLP connector (ablation)X-SAM · segmentor fine-tuning (12 epochs)PQ: 50.1 -> 50.3Improved
add multi-scale features in connector (ablation)X-SAM · segmentor fine-tuning (12 epochs)PQ: 50.3 -> 51.6Improved

Later papers that compared with this method

2 later accepted papers report X-SAM 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