9 citations · 16 across the 8 of their papers we have counts for
9 papers
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.…
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…
Diversity vs. Recognizability: Human-like generalization in one-shot generative models
Victor Boutin, Lakshya Singhal, Xavier Thomas +1
Robust generalization to new concepts has long remained a distinctive feature of human intelligence. However, recent progress in deep generative models has now led to neural archit…
Iterative VAE as a predictive brain model for out-of-distribution generalization
Victor Boutin, Aimen Zerroug, Minju Jung +1
Our ability to generalize beyond training data to novel, out-of-distribution, image degradations is a hallmark of primate vision. The predictive brain, exemplified by predictive co…
5G Simulation-Based Experimentation Framework for Vertical Performance Assessment
Orestes Manzanilla-Salazar, Victor Boutin, Hakim Mellah +2
5G is being designed as a common platform where multiple vertical applications will be able to co-exist and grow in a seamless manner. The diversity of the vertical requirements as…
Effect of top-down connections in Hierarchical Sparse Coding
Victor Boutin, Angelo Franciosini, Franck Ruffier +1
Hierarchical Sparse Coding (HSC) is a powerful model to efficiently represent multi-dimensional, structured data such as images. The simplest solution to solve this computationally…
Sparse Deep Predictive Coding captures contour integration capabilities of the early visual system
Victor Boutin, Angelo Franciosini, Frederic Chavane +2
Both neurophysiological and psychophysical experiments have pointed out the crucial role of recurrent and feedback connections to process context-dependent information in the early…
From biological vision to unsupervised hierarchical sparse coding
Victor Boutin, Angelo Franciosini, Franck Ruffier +1
The formation of connections between neural cells is emerging essentially from an unsupervised learning process. For instance, during the development of the primary visual cortex o…