Vision-language models achieve at most 61.9% accuracy on identifying image distortion types and severities, falling short of human majority-vote performance at 65.7%.
Introducing GPT-5.4.https://openai.com/ index/introducing-gpt-5-4/, 2026
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
DistortBench: Benchmarking Vision Language Models on Image Distortion Identification
Vision-language models achieve at most 61.9% accuracy on identifying image distortion types and severities, falling short of human majority-vote performance at 65.7%.