8 papers
Human-like Object Grouping in Self-supervised Vision Transformers
Hossein Adeli, Seoyoung Ahn, Andrew Luo +3
Vision foundation models trained with self-supervised objectives achieve strong performance across diverse tasks and exhibit emergent object segmentation properties. However, their…
Real-to-Sim for Highly Cluttered Environments via Physics-Consistent Inter-Object Reasoning
Tianyi Xiang, Jiahang Cao, Sikai Guo +3
Reconstructing physically valid 3D scenes from single-view observations is a prerequisite for bridging the gap between visual perception and robotic control. However, in scenarios…
Vision Transformers with Self-Distilled Registers
Yinjie Chen, Zipeng Yan, Chong Zhou +2
Vision Transformers (ViTs) have emerged as the dominant architecture for visual processing tasks, demonstrating excellent scalability with increased training data and model size. H…
Meta-Learning an In-Context Transformer Model of Human Higher Visual Cortex
Muquan Yu, Mu Nan, Hossein Adeli +6
Understanding functional representations within higher visual cortex is a fundamental question in computational neuroscience. While artificial neural networks pretrained on large-s…
In Silico Mapping of Visual Categorical Selectivity Across the Whole Brain
Ethan Hwang, Hossein Adeli, Wenxuan Guo +2
A fine-grained account of functional selectivity in the cortex is essential for understanding how visual information is processed and represented in the brain. Classical studies us…
Brain Mapping with Dense Features: Grounding Cortical Semantic Selectivity in Natural Images With Vision Transformers
Andrew F. Luo, Jacob Yeung, Rushikesh Zawar +4
We introduce BrainSAIL, a method for linking neural selectivity with spatially distributed semantic visual concepts in natural scenes. BrainSAIL leverages recent advances in large-…