AI Paper Atlas

Research map / Detection and segmentation / Weakly supervised detection and segmentation

SAMIX: Reinforcing SAM2 with Semantic Adapter and Reference Selecting Policy for Mix-Supervised Segmentation

Qiang Hu, Jiajie Wei, Zhenyu Yi, Zhifen Yan, Yingjie Guo, Hongkuan Shi, Ge-Peng Ji, Qiang Li, Zhiwei Wang

CVPR 2026 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised semantic segmentation

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 semantic adapter to SAM2 image encoder (without SPNet) (ablation)SAMIX baseline · PASCAL VOC 2012 valmIoU: 66.5 -> 72.5Improved
add SPNet reference selection (without adapter) (ablation)SAMIX baseline · PASCAL VOC 2012 valmIoU: 66.5 -> 68.7Improved
add both adapter and SPNet (ablation)SAMIX baseline · PASCAL VOC 2012 valmIoU: 66.5 -> 75.9Improved
AdaptFormer as adapter instead of naive adapter/LoRA/Med-SA (ablation)SAMIX semantic adapter · PASCAL VOC 2012 valmIoU: 75.5 (LoRA) -> 75.9Improved
use SPNet instead of random reference selection (ablation)SAMIX · PASCAL VOC 2012 valmIoU: 70.4 -> 75.9Improved
use SPNet instead of heuristic sim(F,E) selection (ablation)SAMIX · PASCAL VOC 2012 valmIoU: 72.7 -> 75.9Improved
add Hierarchical Guidance Principle to SPNet (ablation)SPNet · PASCAL VOC 2012 valmIoU: 74.4 -> 75.9Improved
add momentum-updated memory (ablation)SPNet · PASCAL VOC 2012 valmIoU: 75.3 -> 75.9Improved
add consistency reward to quality reward (ablation)SPNet RL rewards · PASCAL VOC 2012 valmIoU: 73.5 -> 75.0Improved
add supervision reward on top of quality and consistency (ablation)SPNet RL rewards · PASCAL VOC 2012 valmIoU: 75.0 -> 75.9Improved
replace SAMIX adapter and SPNet by baseline on COD10K (ablation)SAMIX baseline · COD10K CODSm: 71.8 -> 79.1Improved
switch SAMIX from weakly-supervised to mix-supervision under equal annotation costSAMIX · PASCAL VOC 2012 (equal annotation cost)mIoU: 71.5 -> 73.7Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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