SteelDefectX is a new multi-form vision-language dataset and benchmark for analyzing steel surface defects using 7,778 images across 25 categories.
What does a platypus look like? generating customized prompts for zero-shot image classification
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Dual-modality anchors from text descriptions and test-time image statistics filter views and ensemble predictions to improve test-time prompt tuning, achieving SOTA on 15 datasets.
citing papers explorer
-
SteelDefectX: A Multi-Form Vision-Language Dataset and Benchmark for Steel Surface Defect Analysis
SteelDefectX is a new multi-form vision-language dataset and benchmark for analyzing steel surface defects using 7,778 images across 25 categories.
-
Dual-Modality Anchor-Guided Filtering for Test-time Prompt Tuning
Dual-modality anchors from text descriptions and test-time image statistics filter views and ensemble predictions to improve test-time prompt tuning, achieving SOTA on 15 datasets.