AI Paper Atlas

Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning

What a MESS: Multi-Domain Evaluation of Zero-Shot Semantic Segmentation

Benedikt Blumenstiel, Johannes Jakubik, Hilde Kuehne, Michael Vössing

NeurIPS 2023 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Transductive and semantic-dictionary zero-shot · 4 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
Use CAT-Seg-L instead of Grounded-SAM-L with Grounding DINO promptsMESS multi-domain evaluation · MESS meanmIoU: 29.05 -> 38.14Improved
Use RGB rather than thermal imageryCAT-Seg-L on PST900 · PST900mIoU: 25.26 -> 65.55Improved
Map thermal data to a pseudo color scale instead of using thermal data directlyCAT-Seg-L on PST900 · PST900mIoU: 25.26 -> 25.43No clear effect
Use generic class terminology instead of domain-specific terminologyzero-shot segmentation models on Kvasir-Instrument · Kvasir-InstrumentmIoUImproved
Merge similar classes into a single classzero-shot segmentation models on datasets with similar labels · MESS datasets with similar classesmodel performanceImproved
Use oracle bounding-box prompts instead of text-generated Grounding DINO promptsSAM · MESS meanmIoU: 29.05 -> 75.67Improved

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