4 papers
Semantic Saliency from Multi-Modal Large Language Model Scene Understanding Maps
Ziqi Wen, Shravan Murlidaran, Jonathan Skaza +2
Image-computable low-level image saliency has shaped perceptual psychology and computer science, but is limited by its inability to capture human high-level cognitive factors that…
INTERLACE: Interleaved Layer Pruning and Efficient Adaptation in Large Vision-Language Models
Parsa Madinei, Ryan Solgi, Ziqi Wen +3
We introduce INTERLACE, a novel framework that prunes redundant layers in VLMs while maintaining performance through sample-efficient finetuning. Existing layer pruning methods lea…
DReX: Pure Vision Fusion of Self-Supervised and Convolutional Representations for Image Complexity Prediction
Jonathan Skaza, Parsa Madinei, Ziqi Wen +1
Visual complexity prediction is a fundamental problem in computer vision with applications in image compression, retrieval, and classification. Understanding what makes humans perc…
Predicting Reaction Time to Comprehend Scenes with Foveated Scene Understanding Maps
Ziqi Wen, Jonathan Skaza, Shravan Murlidaran +2
Although models exist that predict human response times (RTs) in tasks such as target search and visual discrimination, the development of image-computable predictors for scene und…