AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

BiPA: Bilevel Prompt Adaptation for Underwater Instance Segmentation

Long Ma, Haoze Zheng, Yuhang Mao, Jinyuan Liu, Chengpei Xu, Xinwei Xue, Yi Wang, Xiangjian He, Weimin Wang

CVPR 2026 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Domain-generalized 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
adapt the dense prompt with bilevel optimization instead of keeping it frozen (ablation)underwater SAM · UIISmAP: 30.9 -> 32.1Improved
naive joint prompt and model training instead of frozen prompt (ablation)underwater SAM · USIS10K (multi-class)mAP: 44.4 -> 43.6Hurt
bilevel prompt adaptation instead of naive joint training (ablation)underwater SAM · USIS10K (multi-class)mAP: 43.6 -> 45.2Improved
add fine-tuning stage with frozen adapted prompt after adaptation stage (ablation)BiPA · UIISmAP: 29.8 -> 32.1Improved
use FAI block instead of simple addition fusion of ResNet50 and ViT features (ablation)BiPA · USIS10K (multi-class)mAP: 43.5 -> 45.2Improved
add FAI block under the frozen prompt strategy (ablation)underwater SAM · UIISmAP: 29.5 -> 30.9Improved
increase optimization interval to B=[1,3] (ablation)BiPA prompt adaptation · UIISmAP: 30.1 -> 32.1Improved
use 16 prompt groups instead of 8 or 32 (ablation)BiPA prompt adaptation · UIISmAP: 31.5 (Ng=8), 30.8 (Ng=32) -> 32.1Improved
BiPA versus USIS-SAM on small objectsBiPA · UIISAPs: 8.1 -> 7.2Hurt
add ResNet50 injection and bilevel adaptation to USIS-SAMUSIS-SAM · UIIS and USIS10Kparameters and FLOPs: +5.59% params, +0.42% FLOPs, +6.95% average mAPMixed

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