Imagen de Portada

FastCAV: Efficient Computation of Concept Activation Vectors for Explaining Deep Neural Networks

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Schmalwasser, Laines, Penzel, Niklas, Denzler, Joachim, Niebling, Julia
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Exploiting Text-Image Latent Spaces for the Description of Visual Concepts
por: Schmalwasser, Laines, et al.
Publicado: (2024)

Locally Explaining Prediction Behavior via Gradual Interventions and Measuring Property Gradients
por: Penzel, Niklas, et al.
Publicado: (2025)

Reducing Bias in Pre-trained Models by Tuning while Penalizing Change
por: Penzel, Niklas, et al.
Publicado: (2024)

When Medical Imaging Met Self-Attention: A Love Story That Didn't Quite Work Out
por: Piater, Tristan, et al.
Publicado: (2024)

Facing Asymmetry -- Uncovering the Causal Link between Facial Symmetry and Expression Classifiers using Synthetic Interventions
por: Büchner, Tim, et al.
Publicado: (2024)

The Power of Properties: Uncovering the Influential Factors in Emotion Classification
por: Büchner, Tim, et al.
Publicado: (2024)

From Neural Activations to Concepts: A Survey on Explaining Concepts in Neural Networks
por: Lee, Jae Hee, et al.
Publicado: (2023)

Saccadic Vision for Fine-Grained Visual Classification
por: Schmidt, Johann, et al.
Publicado: (2025)

Anomalous Agreement: How to find the Ideal Number of Anomaly Classes in Correlated, Multivariate Time Series Data
por: Rewicki, Ferdinand, et al.
Publicado: (2025)

Navigating Neural Space: Revisiting Concept Activation Vectors to Overcome Directional Divergence
por: Pahde, Frederik, et al.
Publicado: (2022)

FaCT: Faithful Concept Traces for Explaining Neural Network Decisions
por: Parchami-Araghi, Amin, et al.
Publicado: (2025)

LG-CAV: Train Any Concept Activation Vector with Language Guidance
por: Huang, Qihan, et al.
Publicado: (2024)

Explaining Explainability: Recommendations for Effective Use of Concept Activation Vectors
por: Nicolson, Angus, et al.
Publicado: (2024)

Modeling COVID-19 Dynamics in German States Using Physics-Informed Neural Networks
por: Rothenbeck, Phillip, et al.
Publicado: (2025)

Explaining Bayesian Neural Networks
por: Bykov, Kirill, et al.
Publicado: (2021)

Explaining How Visual, Textual and Multimodal Encoders Share Concepts
por: Cornet, Clément, et al.
Publicado: (2025)

Improving the Explain-Any-Concept by Introducing Nonlinearity to the Trainable Surrogate Model
por: Zaval, Mounes, et al.
Publicado: (2024)

OMENN: One Matrix to Explain Neural Networks
por: Wróbel, Adam, et al.
Publicado: (2024)

Understanding Multimodal Deep Neural Networks: A Concept Selection View
por: Shang, Chenming, et al.
Publicado: (2024)

Understanding Distributed Representations of Concepts in Deep Neural Networks without Supervision
por: Chang, Wonjoon, et al.
Publicado: (2023)

Concept Visualization: Explaining the CLIP Multi-modal Embedding Using WordNet
por: Giulivi, Loris, et al.
Publicado: (2024)

Achieving Data Efficient Neural Networks with Hybrid Concept-based Models
por: Opsahl, Tobias A., et al.
Publicado: (2024)

DeepIcon: A Hierarchical Network for Layer-wise Icon Vectorization
por: Bing, Qi, et al.
Publicado: (2024)

CoProNN: Concept-based Prototypical Nearest Neighbors for Explaining Vision Models
por: Chiaburu, Teodor, et al.
Publicado: (2024)

Explaining 3D Computed Tomography Classifiers with Counterfactuals
por: Cohen, Joseph Paul, et al.
Publicado: (2025)

KidMesh: Computational Mesh Reconstruction for Pediatric Congenital Hydronephrosis Using Deep Neural Networks
por: Sun, Haoran, et al.
Publicado: (2026)

Towards Human-Understandable Multi-Dimensional Concept Discovery
por: Grobrügge, Arne, et al.
Publicado: (2025)

FastMap: Fast Queries Initialization Based Vectorized HD Map Reconstruction Framework
por: Hu, Haotian, et al.
Publicado: (2025)

Mosaic: Compositional Multi-Concept Erasure via Vector Field Blending
por: Ko, Junseok, et al.
Publicado: (2026)

Unraveling Anomalies in Time: Unsupervised Discovery and Isolation of Anomalous Behavior in Bio-regenerative Life Support System Telemetry
por: Rewicki, Ferdinand, et al.
Publicado: (2024)

On Explaining Visual Captioning with Hybrid Markov Logic Networks
por: Shah, Monika, et al.
Publicado: (2025)

Explaining Generalization Power of a DNN Using Interactive Concepts
por: Zhou, Huilin, et al.
Publicado: (2023)

Token Activation Map to Visually Explain Multimodal LLMs
por: Li, Yi, et al.
Publicado: (2025)

TextCAM: Explaining Class Activation Map with Text
por: Zhao, Qiming, et al.
Publicado: (2025)

DeepJIVE: Learning Joint and Individual Variation Explained from Multimodal Data Using Deep Learning
por: Drexler, Matthew, et al.
Publicado: (2025)

EQ-CBM: A Probabilistic Concept Bottleneck with Energy-based Models and Quantized Vectors
por: Kim, Sangwon, et al.
Publicado: (2024)

Deep Neural Networks Fused with Textures for Image Classification
por: Bera, Asish, et al.
Publicado: (2023)

Enhancing Video Understanding: Deep Neural Networks for Spatiotemporal Analysis
por: Fadaei, Amir Hosein, et al.
Publicado: (2025)

InstantSwap: Fast Customized Concept Swapping across Sharp Shape Differences
por: Zhu, Chenyang, et al.
Publicado: (2024)

Redefining Recon: Bridging Gaps with UAVs, 360 degree Cameras, and Neural Radiance Fields
por: Surmann, Hartmut, et al.
Publicado: (2023)