35 citations · 90 across the 11 of their papers we have counts for
9 papers · 1 filter
FOVI: A biologically-inspired foveated interface for deep vision models
Nicholas M. Blauch, George A. Alvarez, Talia Konkle
Human vision is foveated, with variable resolution peaking at the center of a large field of view; this reflects an efficient trade-off for active sensing, allowing eye-movements t…
Bi-Orthogonal Factor Decomposition for Vision Transformers
Fenil R. Doshi, Thomas Fel, Talia Konkle +1
Self-attention is the central computational primitive of Vision Transformers, yet we lack a principled understanding of what information attention mechanisms exchange between token…
Into the Rabbit Hull: From Task-Relevant Concepts in DINO to Minkowski Geometry
Thomas Fel, Binxu Wang, Michael A. Lepori +8
DINOv2 is routinely deployed to recognize objects, scenes, and actions; yet the nature of what it perceives remains unknown. As a working baseline, we adopt the Linear Representati…
Visual Anagrams Reveal Hidden Differences in Holistic Shape Processing Across Vision Models
Fenil R. Doshi, Thomas Fel, Talia Konkle +1
Humans are able to recognize objects based on both local texture cues and the configuration of object parts, yet contemporary vision models primarily harvest local texture cues, yi…
Archetypal SAE: Adaptive and Stable Dictionary Learning for Concept Extraction in Large Vision Models
Thomas Fel, Ekdeep Singh Lubana, Jacob S. Prince +7
Sparse Autoencoders (SAEs) have emerged as a powerful framework for machine learning interpretability, enabling the unsupervised decomposition of model representations into a dicti…
Understanding Inhibition Through Maximally Tense Images
Chris Hamblin, Srijani Saha, Talia Konkle +1
We address the functional role of 'feature inhibition' in vision models; that is, what are the mechanisms by which a neural network ensures images do not express a given feature? W…
Feature Accentuation: Revealing 'What' Features Respond to in Natural Images
Chris Hamblin, Thomas Fel, Srijani Saha +2
Efforts to decode neural network vision models necessitate a comprehensive grasp of both the spatial and semantic facets governing feature responses within images. Most research ha…
Pruning for Feature-Preserving Circuits in CNNs
Chris Hamblin, Talia Konkle, George Alvarez
Deep convolutional neural networks are a powerful model class for a range of computer vision problems, but it is difficult to interpret the image filtering process they implement,…
Emergent Properties of Foveated Perceptual Systems
Arturo Deza, Talia Konkle
The goal of this work is to characterize the representational impact that foveation operations have for machine vision systems, inspired by the foveated human visual system, which…