Imagen de Portada

LeGrad: An Explainability Method for Vision Transformers via Feature Formation Sensitivity

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Bousselham, Walid, Boggust, Angie, Chaybouti, Sofian, Strobelt, Hendrik, Kuehne, Hilde
Formato:	Preprint
Publicado:	2024
Materias:	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

DEX-AR: A Dynamic Explainability Method for Autoregressive Vision-Language Models
por: Bousselham, Walid, et al.
Publicado: (2026)

MaskInversion: Localized Embeddings via Optimization of Explainability Maps
por: Bousselham, Walid, et al.
Publicado: (2024)

REVEAL: Relation-based Video Representation Learning for Video-Question-Answering
por: Chaybouti, Sofian, et al.
Publicado: (2025)

VOLD: Reasoning Transfer from LLMs to Vision-Language Models via On-Policy Distillation
por: Bousselham, Walid, et al.
Publicado: (2025)

When LLaVA Meets Objects: Token Composition for Vision-Language-Models
por: Jahagirdar, Soumya, et al.
Publicado: (2026)

VideoGEM: Training-free Action Grounding in Videos
por: Vogel, Felix, et al.
Publicado: (2025)

SigLino: Efficient Multi-Teacher Distillation for Agglomerative Vision Foundation Models
por: Chaybouti, Sofian, et al.
Publicado: (2025)

TimeLogic: A Temporal Logic Benchmark for Video QA
por: Swetha, Sirnam, et al.
Publicado: (2025)

HowToCaption: Prompting LLMs to Transform Video Annotations at Scale
por: Shvetsova, Nina, et al.
Publicado: (2023)

Dual Guidance Semi-Supervised Action Detection
por: Singh, Ankit, et al.
Publicado: (2025)

Unbiasing through Textual Descriptions: Mitigating Representation Bias in Video Benchmarks
por: Shvetsova, Nina, et al.
Publicado: (2025)

M2SVid: End-to-End Inpainting and Refinement for Monocular-to-Stereo Video Conversion
por: Shvetsova, Nina, et al.
Publicado: (2025)

DiffusionWorldViewer: Exposing and Broadening the Worldview Reflected by Generative Text-to-Image Models
por: De Simone, Zoe, et al.
Publicado: (2023)

WEAR: An Outdoor Sports Dataset for Wearable and Egocentric Activity Recognition
por: Bock, Marius, et al.
Publicado: (2023)

Creo: From One-Shot Image Generation to Progressive, Co-Creative Ideation
por: De Simone, Zoe, et al.
Publicado: (2026)

VisRes Bench: On Evaluating the Visual Reasoning Capabilities of VLMs
por: Törtei, Brigitta Malagurski, et al.
Publicado: (2025)

Abstraction Alignment: Comparing Model-Learned and Human-Encoded Conceptual Relationships
por: Boggust, Angie, et al.
Publicado: (2024)

Falcon Perception
por: Bevli, Aviraj, et al.
Publicado: (2026)

ViTmiX: Vision Transformer Explainability Augmented by Mixed Visualization Methods
por: Hogea, Eduard, et al.
Publicado: (2024)

Convolutional Differentiable Logic Gate Networks
por: Petersen, Felix, et al.
Publicado: (2024)

MM-TS: Multi-Modal Temperature and Margin Schedules for Contrastive Learning with Long-Tail Data
por: Sheludzko, Siarhei, et al.
Publicado: (2026)

Is Grad-CAM Explainable in Medical Images?
por: Suara, Subhashis, et al.
Publicado: (2023)

TTRV: Test-Time Reinforcement Learning for Vision Language Models
por: Singh, Akshit, et al.
Publicado: (2025)

Evaluating the Explainability of Vision Transformers in Medical Imaging
por: Barekatain, Leili, et al.
Publicado: (2025)

Whisper-Flamingo: Integrating Visual Features into Whisper for Audio-Visual Speech Recognition and Translation
por: Rouditchenko, Andrew, et al.
Publicado: (2024)

Comprehensive Attribution: Inherently Explainable Vision Model with Feature Detector
por: Zhang, Xianren, et al.
Publicado: (2024)

Decision-Aware Attention Propagation for Vision Transformer Explainability
por: Jo, Sehyeong, et al.
Publicado: (2026)

Automated Detection of Defects on Metal Surfaces using Vision Transformers
por: Alaa, Toqa, et al.
Publicado: (2024)

Efficient Masked Face Recognition Method during the COVID-19 Pandemic
por: Hariri, Walid
Publicado: (2021)

Grad-CL: Source Free Domain Adaptation with Gradient Guided Feature Disalignment
por: Thakur, Rini Smita, et al.
Publicado: (2025)

mWhisper-Flamingo for Multilingual Audio-Visual Noise-Robust Speech Recognition
por: Rouditchenko, Andrew, et al.
Publicado: (2025)

LibraGrad: Balancing Gradient Flow for Universally Better Vision Transformer Attributions
por: Mehri, Faridoun, et al.
Publicado: (2024)

Explainable Pathomics Feature Visualization via Correlation-aware Conditional Feature Editing
por: Yang, Yuechen, et al.
Publicado: (2026)

Sensitive Image Classification by Vision Transformers
por: He, Hanxian, et al.
Publicado: (2024)

Q-GroundCAM: Quantifying Grounding in Vision Language Models via GradCAM
por: Rajabi, Navid, et al.
Publicado: (2024)

What, when, and where? -- Self-Supervised Spatio-Temporal Grounding in Untrimmed Multi-Action Videos from Narrated Instructions
por: Chen, Brian, et al.
Publicado: (2023)

Generalizing GradCAM for Embedding Networks
por: Bachhawat, Mudit
Publicado: (2024)

TransUNet-GradCAM: A Hybrid Transformer-U-Net with Self-Attention and Explainable Visualizations for Foot Ulcer Segmentation
por: Asare, Akwasi, et al.
Publicado: (2025)

InFIP: An Explainable DNN Intellectual Property Protection Method based on Intrinsic Features
por: Xue, Mingfu, et al.
Publicado: (2022)

Keypoint Counting Classifiers: Turning Vision Transformers into Self-Explainable Models Without Training
por: Wickstrøm, Kristoffer, et al.
Publicado: (2025)