AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

Probabilistic Prototype Calibration of Vision-language Models for Generalized Few-shot Semantic Segmentation

Jie Liu, Jiayi Shen, Pan Zhou, Jan-Jakob Sonke, Efstratios Gavves

ICCV 2025 · Vision-language and multimodal › CLIP and zero-shot · approach: Open-vocabulary alignment from VLMs · 3 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 prototype calibration (deterministic) to the baseline multi-modal prototypes (ablation)FewCLIP · PASCAL-5i GFSS 1-shotmIoU_N: 33.75 -> 51.36Improved
make prototype calibration probabilistic with distribution regularization (ablation)FewCLIP · PASCAL-5i GFSS 1-shothIoU: 60.79 -> 62.03Improved
make prototype calibration probabilistic (ablation)FewCLIP · PASCAL-5i GFSS 5-shothIoU: 65.22 -> 66.44Improved
use calibration format P_t*P_c+P_t instead of concatenation or other operations (ablation)FewCLIP · PASCAL-5i GFSS 1-shothIoU: 44.76 -> 62.03 (vs additive P_t+P_c)Improved
use both images and class names for novel class registration (ablation)FewCLIP · PASCAL-5i GFSS 1-shothIoU: 46.02 -> 62.03 (vs text only)Improved
fine-tune only the calibration prototypes instead of visual prompts, mask decoder and background prototype (ablation)FewCLIP · PASCAL-5i GFSS 1-shotmIoU_B: 55.93 -> 76.68Improved
fine-tune textual prototypes on novel class samples (ablation)FewCLIP · PASCAL-5i GFSS 1-shothIoU: 46.02 -> 46.83No clear effect
use FewCLIP instead of PoP on COCO-20i 5-shotFewCLIP · COCO-20i GFSS 5-shothIoU: 38.77 -> 38.38Hurt
apply FewCLIP in class-incremental setting instead of PKLPKL · PASCAL-5i CIFSS 1-shot session 5hIoU: 39.00 -> 61.30Improved

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