AI Paper Atlas

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

Global Knowledge Calibration for Fast Open-Vocabulary Segmentation

Kunyang Han, Yong Liu, Jun Hao Liew, Henghui Ding, Jiajun Liu, Yitong Wang, Yansong Tang, Yujiu Yang, Jiashi Feng, Yao Zhao, Yunchao Wei

ICCV 2023 · Detection and segmentation › Open-set and few-shot detection · approach: Open-vocabulary semantic segmentation · 48 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 text diversification (synonyms) to training (ablation)Global Knowledge Calibration (CLIP R-50) · CityscapesmIoU: 27.61 -> 32.16Improved
add text-guided knowledge distillation (ablation)Global Knowledge Calibration (CLIP R-50) · CityscapesmIoU: 27.61 -> 32.62Improved
combine TD and TGKD (ablation)Global Knowledge Calibration (CLIP R-50) · Pascal ContextmIoU: 39.70 -> 41.91Improved
use text-guided instead of vision-guided distillation (ablation)Global Knowledge Calibration · Pascal ContextmIoU: 39.67 -> 41.23Improved
use vision-guided distillation over all regions (vs no KD) (ablation)Global Knowledge Calibration · Pascal ContextmIoU: 39.70 -> 39.67No clear effect
add text diversification to Simbaseline (ablation)Simbaseline · CityscapesmIoU: 30.0 -> 34.7Improved
vary synonym sampling strategy (Random, GroupAvg, GroupMax) (ablation)Text diversification · Pascal ContextmIoU: 41.45 / 41.80 / 41.17No clear effect
use spatial-token teacher and pre-projection student embeddings (ablation)Text-guided KD · CityscapesmIoU: 30.43 -> 32.62Improved
add text-guided KD to video baseline (ablation)Video open-vocab baseline · VIPSeg unseenunseen mIoU: 2.4 -> 2.9Improved
add text diversification on top of KD for video (ablation)Video open-vocab baseline · VIPSeg unseenunseen mIoU: 2.9 -> 8.5Improved
use ImageNet-pretrained backbone instead of CLIP (ablation)Global Knowledge Calibration · Pascal ContextmIoU: 41.9 -> 45.6No clear effect
drop the extra frozen CLIP encoder at inferenceGlobal Knowledge Calibration · Computational cost (R101)FLOPs: 1165.07G -> 151.44GImproved

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