Don't Fight Hallucinations, Use Them: Estimating Image Realism using NLI over Atomic Facts
This addresses the challenge of assessing image realism for AI systems, though it is incremental as it builds on existing LVLM and NLI techniques.
The paper tackles the problem of quantifying image realism by leveraging hallucinations from Large Vision-Language Models (LVLMs) and Natural Language Inference (NLI) to detect common-sense violations, achieving state-of-the-art zero-shot performance on the WHOOPS! dataset.
Quantifying the realism of images remains a challenging problem in the field of artificial intelligence. For example, an image of Albert Einstein holding a smartphone violates common-sense because modern smartphone were invented after Einstein's death. We introduce a novel method for assessing image realism using Large Vision-Language Models (LVLMs) and Natural Language Inference (NLI). Our approach is based on the premise that LVLMs may generate hallucinations when confronted with images that defy common sense. Using LVLM to extract atomic facts from these images, we obtain a mix of accurate facts and erroneous hallucinations. We proceed by calculating pairwise entailment scores among these facts, subsequently aggregating these values to yield a singular reality score. This process serves to identify contradictions between genuine facts and hallucinatory elements, signaling the presence of images that violate common sense. Our approach has achieved a new state-of-the-art performance in zero-shot mode on the WHOOPS! dataset.