Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding
University of Central Florida via YouTube
Overview
Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
Learn about innovative techniques for reducing object hallucinations in Large Vision Language Models (LVLMs) through a 27-minute research presentation from the University of Central Florida. Explore the Visual Contrastive Decoding methodology and its implementation for improving the accuracy and reliability of vision-language models. Examine how this approach helps minimize false object detection and improves the overall performance of LVLMs in real-world applications. Gain insights into the technical aspects of vision-language processing and the latest advancements in reducing AI hallucinations.
Syllabus
Paper 1: Mitigating Object Hallucinations in LVLMs through Visual Contrastive Decoding
Taught by
UCF CRCV