activity
20222026
most citedHarmonizing the object recognition strategies of deep neural networks with humans

11 citations · 23 across the 11 of their papers we have counts for

collaborators
Showing cs.CVShow all

7 papers · 1 filter

cs.CV2026

Structuring Sparsity: Block-Sparse Featurizers Capture Visual Concept Manifolds

Thomas Fel, Matthew Kowal, Mozes Jacobs +22

What is the geometry of a visual percept? The most widely used protocols for decomposing neural network representations into interpretable parts treat concepts as isolated directio…

cs.CV2026

Cross-Modal Redundancy and the Geometry of Vision-Language Embeddings

Grégoire Dhimoïla, Thomas Fel, Victor Boutin +1

Vision-language models (VLMs) align images and text with remarkable success, yet the geometry of their shared embedding space remains poorly understood. To probe this geometry, we…

cs.CV2025

Sparks of Explainability: Recent Advancements in Explaining Large Vision Models

Thomas Fel

This thesis explores advanced approaches to improve explainability in computer vision by analyzing and modeling the features exploited by deep neural networks. Initially, it evalua…

cs.CV2024

Choosing the right basis for interpretability: Psychophysical comparison between neuron-based and dictionary-based representations

Julien Colin, Lore Goetschalckx, Thomas Fel +3

Interpretability research often adopts a neuron-centric lens, treating individual neurons as the fundamental units of explanation. However, neuron-level explanations can be undermi…

cs.CV2024

Understanding Visual Feature Reliance through the Lens of Complexity

Thomas Fel, Louis Bethune, Andrew Kyle Lampinen +2

Recent studies suggest that deep learning models inductive bias towards favoring simpler features may be one of the sources of shortcut learning. Yet, there has been limited focus…

cs.CV2024

Latent Representation Matters: Human-like Sketches in One-shot Drawing Tasks

Victor Boutin, Rishav Mukherji, Aditya Agrawal +4

Humans can effortlessly draw new categories from a single exemplar, a feat that has long posed a challenge for generative models. However, this gap has started to close with recent…