Image de couverture de livre

Unlocking Feature Visualization for Deeper Networks with MAgnitude Constrained Optimization

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Fel, Thomas, Boissin, Thibaut, Boutin, Victor, Picard, Agustin, Novello, Paul, Colin, Julien, Linsley, Drew, Rousseau, Tom, Cadène, Rémi, Goetschalckx, Lore, Gardes, Laurent, Serre, Thomas
Format:	Preprint
Publié:	2023
Sujets:	Computer Vision and Pattern Recognition Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Back to the Baseline: Examining Baseline Effects on Explainability Metrics
par: Picard, Agustin Martin, et autres
Publié: (2025)

Choosing the right basis for interpretability: Psychophysical comparison between neuron-based and dictionary-based representations
par: Colin, Julien, et autres
Publié: (2024)

Capability $\neq$ Interpretability: Human Interpretability of Vision Foundation Models
par: Colin, Julien, et autres
Publié: (2026)

An Adaptive Orthogonal Convolution Scheme for Efficient and Flexible CNN Architectures
par: Boissin, Thibaut, et autres
Publié: (2025)

Cross-Modal Redundancy and the Geometry of Vision-Language Embeddings
par: Dhimoïla, Grégoire, et autres
Publié: (2026)

Better artificial intelligence does not mean better models of biology
par: Linsley, Drew, et autres
Publié: (2025)

On the explainable properties of 1-Lipschitz Neural Networks: An Optimal Transport Perspective
par: Serrurier, Mathieu, et autres
Publié: (2022)

Saliency strikes back: How filtering out high frequencies improves white-box explanations
par: Muzellec, Sabine, et autres
Publié: (2023)

Latent Representation Matters: Human-like Sketches in One-shot Drawing Tasks
par: Boutin, Victor, et autres
Publié: (2024)

Understanding Visual Feature Reliance through the Lens of Complexity
par: Fel, Thomas, et autres
Publié: (2024)

Turbo-Muon: Accelerating Orthogonality-Based Optimization with Pre-Conditioning
par: Boissin, Thibaut, et autres
Publié: (2025)

Sparks of Explainability: Recent Advancements in Explaining Large Vision Models
par: Fel, Thomas
Publié: (2025)

Tracking objects that change in appearance with phase synchrony
par: Muzellec, Sabine, et autres
Publié: (2024)

Not Too Generative, Not Too Discriminative: The Human Alignment Sweet Spot
par: Ortega, Jorge Chang, et autres
Publié: (2026)

Robust One-Class Classification with Signed Distance Function using 1-Lipschitz Neural Networks
par: Bethune, Louis, et autres
Publié: (2023)

The 3D-PC: a benchmark for visual perspective taking in humans and machines
par: Linsley, Drew, et autres
Publié: (2024)

Orthogonium : A Unified, Efficient Library of Orthogonal and 1-Lipschitz Building Blocks
par: Boissin, Thibaut, et autres
Publié: (2026)

ConSim: Measuring Concept-Based Explanations' Effectiveness with Automated Simulatability
par: Poché, Antonin, et autres
Publié: (2025)

Increasing the Diversity in RGB-to-Thermal Image Translation for Automotive Applications
par: Wang, Kaili, et autres
Publié: (2025)

Follow the Energy, Find the Path: Riemannian Metrics from Energy-Based Models
par: Béthune, Louis, et autres
Publié: (2025)

From Prediction to Understanding: Will AI Foundation Models Transform Brain Science?
par: Serre, Thomas, et autres
Publié: (2025)

Comparison of Weibull tail-coefficient estimators
par: Gardes, Laurent, et autres
Publié: (2011)

Extreme Conditional Quantile Estimation in High Dimensions: A Comparative Study
par: Laurent Gardes, et autres
Publié: (2026)

Efficient Robust Conformal Prediction via Lipschitz-Bounded Networks
par: Massena, Thomas, et autres
Publié: (2025)

The Deep Latent Position Block Model For The Block Clustering And Latent Representation Of Networks
par: Boutin, Rémi, et autres
Publié: (2024)

The Deep Latent Position Topic Model for Clustering and Representation of Networks with Textual Edges
par: Boutin, Rémi, et autres
Publié: (2023)

Monte Carlo methods on compact complex manifolds using Bergman kernels
par: Lemoine, Thibaut, et autres
Publié: (2024)

Unlocking Exploration in RLVR: Uncertainty-aware Advantage Shaping for Deeper Reasoning
par: Xie, Can, et autres
Publié: (2025)

Análisis bibliométrico de la teoría de gestión estratégica basada en recursos y competencias
par: Jean-Pierre Boissin
Publié: (2003)

Isotropic conductivity of two-dimensional three- and four-phase symmetric composites: duality and universal bounds
par: Fel, Leonid
Publié: (2025)

A Geometric Unification of Concept Learning with Concept Cones
par: Rocchi--Henry, Alexandre, et autres
Publié: (2025)

Two-step aging dynamics in enzymatic milk gels
par: Bauland, Julien, et autres
Publié: (2024)

Florida Interlibrary Loan Improvement Project. Final Report.
par: Linsley, Laurie S.
Publié: (1980)

Academic Libraries in an Interlibrary Loan Network.
par: Linsley, Laurie S.
Publié: (1982)

Compensated Integrability in bounded domains ; Applications to gases
par: Serre, Denis
Publié: (2024)

Editorial of the Special Issue “Flood Risk and Resilience in Coastal Zones and Tropical Islands”
par: Damien Serre
Publié: (2025)

Towards the Training of Deeper Predictive Coding Neural Networks
par: Qi, Chang, et autres
Publié: (2025)

Uncovering Intermediate Variables in Transformers using Circuit Probing
par: Lepori, Michael A., et autres
Publié: (2023)

DeFiNES: Enabling Fast Exploration of the Depth-first Scheduling Space for DNN Accelerators through Analytical Modeling
par: Mei, Linyan, et autres
Publié: (2022)

DP-SGD Without Clipping: The Lipschitz Neural Network Way
par: Bethune, Louis, et autres
Publié: (2023)