Vision-language models can't handle queries with negation words, study shows

Study shows vision-language models can't handle queries with negation words

Researchers found that vision-language models, widely used to analyze medical images, do not understand negation words like 'no' and 'not.' This could cause them to fail unexpectedly when asked to retrieve medical images that contain certain objects but not others.

Vision-language models can't handle queries with negation words, study shows

Imagine a radiologist examining a chest X-ray from a new patient. She notices the patient has swelling in the tissue but does not have an enlarged heart. Looking to speed up diagnosis, she might use a vision-language machine-learning model to search for reports from similar patients.

A.I. Was Coming for Radiologists’ Jobs. So Far, They’re Just More Efficient.

Nine years ago, one of the world’s leading artificial intelligence scientists singled out an endangered... The post A.I. Was Coming for Radiologists’ Jobs. So Far, They’re Just More Efficient. appeared first on .