Copertina

[Re] Improving Interpretation Faithfulness for Vision Transformers

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Kurek, Izabela, Trejter, Wojciech, Frkovic, Stipe, Erdelez, Andro
Natura:	Preprint
Pubblicazione:	2025
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

Improving Interpretation Faithfulness for Vision Transformers
di: Hu, Lijie, et al.
Pubblicazione: (2023)

Can Cross-Layer Transcoders Replace Vision Transformer Activations? An Interpretable Perspective on Vision
di: Chatzoudis, Gerasimos, et al.
Pubblicazione: (2026)

Prompt-CAM: Making Vision Transformers Interpretable for Fine-Grained Analysis
di: Chowdhury, Arpita, et al.
Pubblicazione: (2025)

Explanation-Driven Counterfactual Testing for Faithfulness in Vision-Language Model Explanations
di: Ding, Sihao, et al.
Pubblicazione: (2025)

Improved Ear Verification with Vision Transformers and Overlapping Patches
di: Arun, Deeksha, et al.
Pubblicazione: (2025)

Dynamic Accumulated Attention Map for Interpreting Evolution of Decision-Making in Vision Transformer
di: Liao, Yi, et al.
Pubblicazione: (2025)

ProtoPFormer: Concentrating on Prototypical Parts in Vision Transformers for Interpretable Image Recognition
di: Xue, Mengqi, et al.
Pubblicazione: (2022)

Cognitive Alignment At No Cost: Inducing Human Attention Biases For Interpretable Vision Transformers
di: Knights, Ethan
Pubblicazione: (2026)

IFViT: Interpretable Fixed-Length Representation for Fingerprint Matching via Vision Transformer
di: Qiu, Yuhang, et al.
Pubblicazione: (2024)

SPD-Faith Bench: Diagnosing and Improving Faithfulness in Chain-of-Thought for Multimodal Large Language Models
di: Lv, Weijiang, et al.
Pubblicazione: (2026)

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers
di: Xu, Xuwei, et al.
Pubblicazione: (2025)

MSVIT: Improving Spiking Vision Transformer Using Multi-scale Attention Fusion
di: Hua, Wei, et al.
Pubblicazione: (2025)

MDS-ViTNet: Improving saliency prediction for Eye-Tracking with Vision Transformer
di: Ignat, Polezhaev, et al.
Pubblicazione: (2024)

Systematic Evaluation of Vision Transformers for Automated Cervical Cancer Classification: Optimization, Statistical Validation, and Clinical Interpretability
di: Albzour, Nisreen, et al.
Pubblicazione: (2026)

Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers
di: Vielhaben, Johanna, et al.
Pubblicazione: (2024)

FaithfulFaces: Pose-Faithful Facial Identity Preservation for Text-to-Video Generation
di: Wang, Yuanzhi, et al.
Pubblicazione: (2026)

Faithful GRPO: Improving Visual Spatial Reasoning in Multimodal Language Models via Constrained Policy Optimization
di: Kancheti, Sai Srinivas, et al.
Pubblicazione: (2026)

FaithSCAN: Model-Driven Single-Pass Hallucination Detection for Faithful Visual Question Answering
di: Tong, Chaodong, et al.
Pubblicazione: (2026)

Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models
di: Rahman, Md Ashikur, et al.
Pubblicazione: (2026)

From Pixels to Explanations: Interpretable Diabetic Retinopathy Grading with CNN-Transformer Ensembles, Visual Explainability and Vision-Language Models
di: Khokhar, Pir Bakhsh, et al.
Pubblicazione: (2026)

Transformer for Object Re-Identification: A Survey
di: Ye, Mang, et al.
Pubblicazione: (2024)

Causal Interpretation of Sparse Autoencoder Features in Vision
di: Han, Sangyu, et al.
Pubblicazione: (2025)

On the Faithfulness of Visual Thinking: Measurement and Enhancement
di: Liu, Zujing, et al.
Pubblicazione: (2025)

FACE: Faithful Automatic Concept Extraction
di: Bhusal, Dipkamal, et al.
Pubblicazione: (2025)

Case-Enhanced Vision Transformer: Improving Explanations of Image Similarity with a ViT-based Similarity Metric
di: Zhao, Ziwei, et al.
Pubblicazione: (2024)

Interpretable Debiasing of Vision-Language Models for Social Fairness
di: An, Na Min, et al.
Pubblicazione: (2026)

Vision Bridge Transformer at Scale
di: Tan, Zhenxiong, et al.
Pubblicazione: (2025)

Benchmarking Unlearning for Vision Transformers
di: Zhao, Kairan, et al.
Pubblicazione: (2026)

Improving Video Diffusion Transformer Training by Multi-Feature Fusion and Alignment from Self-Supervised Vision Encoders
di: Lee, Dohun, et al.
Pubblicazione: (2025)

Stake the Points: Structure-Faithful Instance Unlearning
di: Hong, Kiseong, et al.
Pubblicazione: (2026)

Towards Faithful Reasoning in Comics for Small MLLMs
di: Feng, Chengcheng, et al.
Pubblicazione: (2026)

IPGPhormer: Interpretable Pathology Graph-Transformer for Survival Analysis
di: Tang, Guo, et al.
Pubblicazione: (2025)

Training Transitive and Commutative Multimodal Transformers with LoReTTa
di: Tran, Manuel, et al.
Pubblicazione: (2023)

Adaptive High-Frequency Transformer for Diverse Wildlife Re-Identification
di: Li, Chenyue, et al.
Pubblicazione: (2024)

Gnothi Seauton: Empowering Faithful Self-Interpretability in Black-Box Transformers
di: Wang, Shaobo, et al.
Pubblicazione: (2024)

Enhancing Interpretability for Vision Models via Shapley Value Optimization
di: Fan, Kanglong, et al.
Pubblicazione: (2025)

The Cartesian Shortcut: Re-evaluate Vision Reasoning in Polar Coordinate Space
di: Hu, Xia, et al.
Pubblicazione: (2026)

Improving Diffusion-Based Image Editing Faithfulness via Guidance and Scheduling
di: Cho, Hansam, et al.
Pubblicazione: (2025)

Improved Belief-Attention in Vision Task
di: Zhang, Guoqiang
Pubblicazione: (2026)

The Linear Attention Resurrection in Vision Transformer
di: Zheng, Chuanyang
Pubblicazione: (2025)