Imagen de Portada

Inside-Out: Measuring Generalization in Vision Transformers Through Inner Workings

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Peng, Yunxiang, Ma, Mengmeng, Yao, Ziyu, Peng, Xi
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning 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

DEAL: Disentangle and Localize Concept-level Explanations for VLMs
por: Li, Tang, et al.
Publicado: (2024)

Beyond Accuracy: Ensuring Correct Predictions With Correct Rationales
por: Li, Tang, et al.
Publicado: (2024)

Attention Transfer Is Not Universally Effective for Vision Transformers
por: Qin, Huaiyuan, et al.
Publicado: (2026)

Out-Of-Distribution Detection with Diversification (Provably)
por: Yao, Haiyun, et al.
Publicado: (2024)

Debiased Negative Mining Improves Out-of-distribution Detection with Pre-trained Vision-Language Models
por: Peng, Bo, et al.
Publicado: (2026)

Slicing Vision Transformer for Flexible Inference
por: Zhang, Yitian, et al.
Publicado: (2024)

Recovering Global Data Distribution Locally in Federated Learning
por: Yao, Ziyu
Publicado: (2024)

Efficient Adaptation of Large Vision Transformer via Adapter Re-Composing
por: Dong, Wei, et al.
Publicado: (2023)

Point Cloud Synthesis Using Inner Product Transforms
por: Röell, Ernst, et al.
Publicado: (2024)

When Accuracy Is Not Enough: Uncertainty Collapse between Noisy Label Learning and Out-of-Distribution Detection
por: Peng, Ningkang, et al.
Publicado: (2026)

SeafloorAI: A Large-scale Vision-Language Dataset for Seafloor Geological Survey
por: Nguyen, Kien X., et al.
Publicado: (2024)

Privacy-Preserving in Connected and Autonomous Vehicles Through Vision to Text Transformation
por: Rezaei, Abdolazim, et al.
Publicado: (2025)

SOLO: A Single Transformer for Scalable Vision-Language Modeling
por: Chen, Yangyi, et al.
Publicado: (2024)

DUDE: Diffusion-Based Unsupervised Cross-Domain Image Retrieval
por: Yang, Ruohong, et al.
Publicado: (2025)

Benchmarking Bias Mitigation Toward Fairness Without Harm from Vision to LVLMs
por: Tan, Xuwei, et al.
Publicado: (2026)

Relating CNN-Transformer Fusion Network for Change Detection
por: Gao, Yuhao, et al.
Publicado: (2024)

WriteViT: Handwritten Text Generation with Vision Transformer
por: Nam, Dang Hoai, et al.
Publicado: (2025)

Optimal Transport-Induced Samples against Out-of-Distribution Overconfidence
por: Tang, Keke, et al.
Publicado: (2026)

T-QPM: Enabling Temporal Out-Of-Distribution Detection and Domain Generalization for Vision-Language Models in Open-World
por: Naiknaware, Aditi, et al.
Publicado: (2026)

Matryoshka Query Transformer for Large Vision-Language Models
por: Hu, Wenbo, et al.
Publicado: (2024)

Image Restoration Through Generalized Ornstein-Uhlenbeck Bridge
por: Yue, Conghan, et al.
Publicado: (2023)

Cross-modal Active Complementary Learning with Self-refining Correspondence
por: Qin, Yang, et al.
Publicado: (2023)

DiFiC: Your Diffusion Model Holds the Secret to Fine-Grained Clustering
por: Yang, Ruohong, et al.
Publicado: (2024)

Rethinking the Use of Vision Transformers for AI-Generated Image Detection
por: Park, NaHyeon, et al.
Publicado: (2025)

Self-Calibrated Tuning of Vision-Language Models for Out-of-Distribution Detection
por: Yu, Geng, et al.
Publicado: (2024)

Scaling Continual Learning to 300+ Tasks with Bi-Level Routing Mixture-of-Experts
por: Lou, Meng, et al.
Publicado: (2026)

LAION-C: An Out-of-Distribution Benchmark for Web-Scale Vision Models
por: Li, Fanfei, et al.
Publicado: (2025)

Unveil Benign Overfitting for Transformer in Vision: Training Dynamics, Convergence, and Generalization
por: Jiang, Jiarui, et al.
Publicado: (2024)

On the Detection of Anomalous or Out-Of-Distribution Data in Vision Models Using Statistical Techniques
por: O'Mahony, Laura, et al.
Publicado: (2024)

Detecting Out-of-Distribution Objects through Class-Conditioned Inpainting
por: Nguyen, Quang-Huy, et al.
Publicado: (2024)

Understanding the Failure Modes of Out-of-Distribution Generalization
por: Nagarajan, Vaishnavh, et al.
Publicado: (2020)

Native Segmentation Vision Transformers
por: Brasó, Guillem, et al.
Publicado: (2025)

Octic Vision Transformers: Quicker ViTs Through Equivariance
por: Nordström, David, et al.
Publicado: (2025)

Learning with Mixture of Prototypes for Out-of-Distribution Detection
por: Lu, Haodong, et al.
Publicado: (2024)

Oscillation-Reduced MXFP4 Training for Vision Transformers
por: Chen, Yuxiang, et al.
Publicado: (2025)

ELSA: Exact Linear-Scan Attention for Fast and Memory-Light Vision Transformers
por: Hsu, Chih-Chung, et al.
Publicado: (2026)

SelaFD:Seamless Adaptation of Vision Transformer Fine-tuning for Radar-based Human Activity Recognition
por: Wang, Yijun, et al.
Publicado: (2025)

Noise-Aware Generalization: Robustness to In-Domain Noise and Out-of-Domain Generalization
por: Wang, Siqi, et al.
Publicado: (2025)

BOOD: Boundary-based Out-Of-Distribution Data Generation
por: Liao, Qilin, et al.
Publicado: (2025)

Hypercone Assisted Contour Generation for Out-of-Distribution Detection
por: Vapsi, Annita, et al.
Publicado: (2025)