SIGIR 2024 M1.4 [fp] Invisible Relevance Bias: Text-Image Retrieval Models Prefer AI-Generated Image
Why it's on BrighterTube
Advanced · Hand-picked by a BrighterTube curator · found via round-3 back catalogue of a channel Lumen picks video by video · 82% confidenceIdentifies bias toward AI-generated images in text-to-image retrieval models. Empirical analysis of fairness issues in multimodal neural systems.
What you'll learn
A 12-minute video from Association for Computing Machinery (ACM): “SIGIR 2024 M1.4 [fp] Invisible Relevance Bias: Text-Image Retrieval Models Prefer AI-Generated Image”.
Video by Association for Computing Machinery (ACM), played through YouTube's embedded player.
Part of ACM SIGIR Conference 2024