4 papers · 1 filter
Pruning the Paradox: How CLIP's Most Informative Heads Enhance Performance While Amplifying Bias
Avinash Madasu, Vasudev Lal, Phillip Howard
CLIP is one of the most popular foundation models and is heavily used for many vision-language tasks, yet little is known about its inner workings. As CLIP is increasingly deployed…
Quantifying and Enabling the Interpretability of CLIP-like Models
Avinash Madasu, Yossi Gandelsman, Vasudev Lal +1
CLIP is one of the most popular foundational models and is heavily used for many vision-language tasks. However, little is known about the inner workings of CLIP. To bridge this ga…
ICSVR: Investigating Compositional and Syntactic Understanding in Video Retrieval Models
Avinash Madasu, Vasudev Lal
Video retrieval (VR) involves retrieving the ground truth video from the video database given a text caption or vice-versa. The two important components of compositionality: object…
SocialCounterfactuals: Probing and Mitigating Intersectional Social Biases in Vision-Language Models with Counterfactual Examples
Phillip Howard, Avinash Madasu, Tiep Le +3
While vision-language models (VLMs) have achieved remarkable performance improvements recently, there is growing evidence that these models also posses harmful biases with respect…