11 citations · 74 across the 29 of their papers we have counts for
29 papers
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…
A Unifying Framework for Concept-Based Representational Similarity
Grégoire Dhimoïla, Victor Boutin, Agustin Martin Picard +2
Learned representations across models and modalities often exhibit striking structural similarities, suggesting shared underlying concept decompositions. However, concept alignment…
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…
Back to the Baseline: Examining Baseline Effects on Explainability Metrics
Agustin Martin Picard, Thibaut Boissin, Varshini Subhash +2
Attribution methods are among the most prevalent techniques in Explainable Artificial Intelligence (XAI) and are usually evaluated and compared using Fidelity metrics, with Inserti…
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…
An Adaptive Orthogonal Convolution Scheme for Efficient and Flexible CNN Architectures
Thibaut Boissin, Franck Mamalet, Thomas Fel +3
Orthogonal convolutional layers are valuable components in multiple areas of machine learning, such as adversarial robustness, normalizing flows, GANs, and Lipschitz-constrained mo…
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…
One Wave To Explain Them All: A Unifying Perspective On Feature Attribution
Gabriel Kasmi, Amandine Brunetto, Thomas Fel +1
Feature attribution methods aim to improve the transparency of deep neural networks by identifying the input features that influence a model's decision. Pixel-based heatmaps have b…
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…
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…
Saliency strikes back: How filtering out high frequencies improves white-box explanations
Sabine Muzellec, Thomas Fel, Victor Boutin +3
Attribution methods correspond to a class of explainability methods (XAI) that aim to assess how individual inputs contribute to a model's decision-making process. We have identifi…
Performance-optimized deep neural networks are evolving into worse models of inferotemporal visual cortex
Drew Linsley, Ivan F. Rodriguez, Thomas Fel +4
One of the most impactful findings in computational neuroscience over the past decade is that the object recognition accuracy of deep neural networks (DNNs) correlates with their a…
Adversarial alignment: Breaking the trade-off between the strength of an attack and its relevance to human perception
Drew Linsley, Pinyuan Feng, Thibaut Boissin +4
Deep neural networks (DNNs) are known to have a fundamental sensitivity to adversarial attacks, perturbations of the input that are imperceptible to humans yet powerful enough to c…
A Holistic Approach to Unifying Automatic Concept Extraction and Concept Importance Estimation
Thomas Fel, Victor Boutin, Mazda Moayeri +5
In recent years, concept-based approaches have emerged as some of the most promising explainability methods to help us interpret the decisions of Artificial Neural Networks (ANNs).…
Unlocking Feature Visualization for Deeper Networks with MAgnitude Constrained Optimization
Thomas Fel, Thibaut Boissin, Victor Boutin +9
Feature visualization has gained substantial popularity, particularly after the influential work by Olah et al. in 2017, which established it as a crucial tool for explainability.…
COCKATIEL: COntinuous Concept ranKed ATtribution with Interpretable ELements for explaining neural net classifiers on NLP tasks
Fanny Jourdan, Agustin Picard, Thomas Fel +3
Transformer architectures are complex and their use in NLP, while it has engendered many successes, makes their interpretability or explainability challenging. Recent debates have…
Confident Object Detection via Conformal Prediction and Conformal Risk Control: an Application to Railway Signaling
Léo Andéol, Thomas Fel, Florence De Grancey +1
Deploying deep learning models in real-world certified systems requires the ability to provide confidence estimates that accurately reflect their uncertainty. In this paper, we dem…
Conformal Prediction for Trustworthy Detection of Railway Signals
Léo Andéol, Thomas Fel, Florence De Grancey +1
We present an application of conformal prediction, a form of uncertainty quantification with guarantees, to the detection of railway signals. State-of-the-art architectures are tes…
Diffusion Models as Artists: Are we Closing the Gap between Humans and Machines?
Victor Boutin, Thomas Fel, Lakshya Singhal +4
An important milestone for AI is the development of algorithms that can produce drawings that are indistinguishable from those of humans. Here, we adapt the 'diversity vs. recogniz…
Harmonizing the object recognition strategies of deep neural networks with humans
Thomas Fel, Ivan Felipe, Drew Linsley +1
The many successes of deep neural networks (DNNs) over the past decade have largely been driven by computational scale rather than insights from biological intelligence. Here, we e…
CRAFT: Concept Recursive Activation FacTorization for Explainability
Thomas Fel, Agustin Picard, Louis Bethune +5
Attribution methods, which employ heatmaps to identify the most influential regions of an image that impact model decisions, have gained widespread popularity as a type of explaina…
Conviformers: Convolutionally guided Vision Transformer
Mohit Vaishnav, Thomas Fel, Ivań Felipe Rodríguez +1
Vision transformers are nowadays the de-facto choice for image classification tasks. There are two broad categories of classification tasks, fine-grained and coarse-grained. In fin…
Xplique: A Deep Learning Explainability Toolbox
Thomas Fel, Lucas Hervier, David Vigouroux +12
Today's most advanced machine-learning models are hardly scrutable. The key challenge for explainability methods is to help assisting researchers in opening up these black boxes, b…
On the explainable properties of 1-Lipschitz Neural Networks: An Optimal Transport Perspective
Mathieu Serrurier, Franck Mamalet, Thomas Fel +2
Input gradients have a pivotal role in a variety of applications, including adversarial attack algorithms for evaluating model robustness, explainable AI techniques for generating…