Copertina

Understanding Visual Feature Reliance through the Lens of Complexity

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Fel, Thomas, Bethune, Louis, Lampinen, Andrew Kyle, Serre, Thomas, Hermann, Katherine
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computer Vision and Pattern Recognition Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Unlocking Feature Visualization for Deeper Networks with MAgnitude Constrained Optimization
di: Fel, Thomas, et al.
Pubblicazione: (2023)

On the explainable properties of 1-Lipschitz Neural Networks: An Optimal Transport Perspective
di: Serrurier, Mathieu, et al.
Pubblicazione: (2022)

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

Saliency strikes back: How filtering out high frequencies improves white-box explanations
di: Muzellec, Sabine, et al.
Pubblicazione: (2023)

1-Lipschitz Neural Distance Fields
di: Coiffier, Guillaume, et al.
Pubblicazione: (2024)

Visual Anagrams Reveal Hidden Differences in Holistic Shape Processing Across Vision Models
di: Doshi, Fenil R., et al.
Pubblicazione: (2025)

Revisiting Visual Understanding in Multimodal Reasoning through a Lens of Image Perturbation
di: Li, Yuting, et al.
Pubblicazione: (2025)

Bi-Orthogonal Factor Decomposition for Vision Transformers
di: Doshi, Fenil R., et al.
Pubblicazione: (2026)

Better artificial intelligence does not mean better models of biology
di: Linsley, Drew, et al.
Pubblicazione: (2025)

Learned feature representations are biased by complexity, learning order, position, and more
di: Lampinen, Andrew Kyle, et al.
Pubblicazione: (2024)

A Geometric Unification of Concept Learning with Concept Cones
di: Rocchi--Henry, Alexandre, et al.
Pubblicazione: (2025)

Not Too Generative, Not Too Discriminative: The Human Alignment Sweet Spot
di: Ortega, Jorge Chang, et al.
Pubblicazione: (2026)

Back to the Baseline: Examining Baseline Effects on Explainability Metrics
di: Picard, Agustin Martin, et al.
Pubblicazione: (2025)

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders
di: Bohacek, Matyas, et al.
Pubblicazione: (2025)

Complexity in Complexity: Understanding Visual Complexity Through Structure, Color, and Surprise
di: Sarıtaş, Karahan, et al.
Pubblicazione: (2025)

Enhancing Visual Reliance in Text Generation: A Bayesian Perspective on Mitigating Hallucination in Large Vision-Language Models
di: Hu, Nanxing, et al.
Pubblicazione: (2025)

Aligning Machine and Human Visual Representations across Abstraction Levels
di: Muttenthaler, Lukas, et al.
Pubblicazione: (2024)

Unearthing Skill-Level Insights for Understanding Trade-Offs of Foundation Models
di: Moayeri, Mazda, et al.
Pubblicazione: (2024)

Understanding Visual Concepts Across Models
di: Trabucco, Brandon, et al.
Pubblicazione: (2024)

Choosing the right basis for interpretability: Psychophysical comparison between neuron-based and dictionary-based representations
di: Colin, Julien, et al.
Pubblicazione: (2024)

Interpreting Physics in Video World Models
di: Joseph, Sonia, et al.
Pubblicazione: (2026)

TruthLens: Visual Grounding for Universal DeepFake Reasoning
di: Kundu, Rohit, et al.
Pubblicazione: (2025)

LatentLens: Revealing Highly Interpretable Visual Tokens in LLMs
di: Krojer, Benno, et al.
Pubblicazione: (2026)

TruthLens:A Training-Free Paradigm for DeepFake Detection
di: Chakraborty, Ritabrata, et al.
Pubblicazione: (2025)

Beyond the Doors of Perception: Vision Transformers Represent Relations Between Objects
di: Lepori, Michael A., et al.
Pubblicazione: (2024)

LensVLM: Selective Context Expansion for Compressed Visual Representation of Text
di: Xie, Roy, et al.
Pubblicazione: (2026)

LensWalk: Agentic Video Understanding by Planning How You See in Videos
di: Li, Keliang, et al.
Pubblicazione: (2026)

Probing Vision-Language Understanding through the Visual Entailment Task: promises and pitfalls
di: Pitta, Elena, et al.
Pubblicazione: (2025)

UniToken: Harmonizing Multimodal Understanding and Generation through Unified Visual Encoding
di: Jiao, Yang, et al.
Pubblicazione: (2025)

Into the Rabbit Hull: From Task-Relevant Concepts in DINO to Minkowski Geometry
di: Fel, Thomas, et al.
Pubblicazione: (2025)

Understanding Figurative Meaning through Explainable Visual Entailment
di: Saakyan, Arkadiy, et al.
Pubblicazione: (2024)

Block-Recurrent Dynamics in Vision Transformers
di: Jacobs, Mozes, et al.
Pubblicazione: (2025)

Detection and Pose Estimation of flat, Texture-less Industry Objects on HoloLens using synthetic Training
di: Pöllabauer, Thomas, et al.
Pubblicazione: (2024)

R-LLaVA: Improving Med-VQA Understanding through Visual Region of Interest
di: Chen, Xupeng, et al.
Pubblicazione: (2024)

Countering the Over-Reliance Trap: Mitigating Object Hallucination for LVLMs via a Self-Validation Framework
di: Liu, Shiyu, et al.
Pubblicazione: (2026)

Enhancing deep neural networks through complex-valued representations and Kuramoto synchronization dynamics
di: Muzellec, Sabine, et al.
Pubblicazione: (2025)

Understanding Graphical Perception in Data Visualization through Zero-shot Prompting of Vision-Language Models
di: Guo, Grace, et al.
Pubblicazione: (2024)

Towards Understanding Visual Grounding in Visual Language Models
di: Pantazopoulos, Georgios, et al.
Pubblicazione: (2025)

Creating a Lens of Chinese Culture: A Multimodal Dataset for Chinese Pun Rebus Art Understanding
di: Zhang, Tuo, et al.
Pubblicazione: (2024)

Binding Visual Features Point by Point
di: Haputhanthri, Udith, et al.
Pubblicazione: (2026)