Cover Image

Unveil Benign Overfitting for Transformer in Vision: Training Dynamics, Convergence, and Generalization

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Jiang, Jiarui, Huang, Wei, Zhang, Miao, Suzuki, Taiji, Nie, Liqiang
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Benign, Tempered, or Catastrophic: A Taxonomy of Overfitting
by: Mallinar, Neil, et al.
Published: (2022)

Trained Mamba Emulates Online Gradient Descent in In-Context Linear Regression
by: Jiang, Jiarui, et al.
Published: (2025)

Deep Exploration of Epoch-wise Double Descent in Noisy Data: Signal Separation, Large Activation, and Benign Overfitting
by: Kubo, Tomoki, et al.
Published: (2026)

FREPix: Frequency-Heterogeneous Flow Matching for Pixel-Space Image Generation
by: Lin, Mingfeng, et al.
Published: (2026)

Handling Imbalanced Pseudolabels for Vision-Language Models with Concept Alignment and Confusion-Aware Calibrated Margin
by: Wang, Yuchen, et al.
Published: (2025)

Preventing Catastrophic Overfitting in Fast Adversarial Training: A Bi-level Optimization Perspective
by: Wang, Zhaoxin, et al.
Published: (2024)

Models as Lego Builders: Assembling Malice from Benign Blocks via Semantic Blueprints
by: Li, Chenxi, et al.
Published: (2026)

Fair Deepfake Detectors Can Generalize
by: Cheng, Harry, et al.
Published: (2025)

Block Selective Reprogramming for On-device Training of Vision Transformers
by: Sarkar, Sreetama, et al.
Published: (2024)

Unveil Inversion and Invariance in Flow Transformer for Versatile Image Editing
by: Xu, Pengcheng, et al.
Published: (2024)

Data Overfitting for On-Device Super-Resolution with Dynamic Algorithm and Compiler Co-Design
by: Li, Gen, et al.
Published: (2024)

ViTGAN: Training GANs with Vision Transformers
by: Lee, Kwonjoon, et al.
Published: (2021)

DKDM: Data-Free Knowledge Distillation for Diffusion Models with Any Architecture
by: Xiang, Qianlong, et al.
Published: (2024)

Contrastive Forward-Forward: A Training Algorithm of Vision Transformer
by: Aghagolzadeh, Hossein, et al.
Published: (2025)

Inducing Spatial Locality in Vision Transformers through the Training Protocol
by: Toledo, Eduardo Santiago, et al.
Published: (2026)

Unveiling the Dynamics of Information Interplay in Supervised Learning
by: Song, Kun, et al.
Published: (2024)

UtilGen: Utility-Centric Generative Data Augmentation with Dual-Level Task Adaptation
by: Guo, Jiyu, et al.
Published: (2025)

Efficient and Long-Tailed Generalization for Pre-trained Vision-Language Model
by: Shi, Jiang-Xin, et al.
Published: (2024)

Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think
by: Yu, Sihyun, et al.
Published: (2024)

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

ViTNT-FIQA: Training-Free Face Image Quality Assessment with Vision Transformers
by: Ozgur, Guray, et al.
Published: (2026)

Fast Training of Diffusion Models with Masked Transformers
by: Zheng, Hongkai, et al.
Published: (2023)

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

Source-Free Domain Adaptation Guided by Vision and Vision-Language Pre-Training
by: Zhang, Wenyu, et al.
Published: (2024)

ELSA: Exploiting Layer-wise N:M Sparsity for Vision Transformer Acceleration
by: Huang, Ning-Chi, et al.
Published: (2024)

Open Multimodal Retrieval-Augmented Factual Image Generation
by: Tian, Yang, et al.
Published: (2025)

Split Adaptation for Pre-trained Vision Transformers
by: Wang, Lixu, et al.
Published: (2025)

Perturbing the Gradient for Alleviating Meta Overfitting
by: Gogoi, Manas, et al.
Published: (2024)

Adversarially Diversified Rehearsal Memory (ADRM): Mitigating Memory Overfitting Challenge in Continual Learning
by: Khan, Hikmat, et al.
Published: (2024)

HandsOnVLM: Vision-Language Models for Hand-Object Interaction Prediction
by: Bao, Chen, et al.
Published: (2024)

VLG-CBM: Training Concept Bottleneck Models with Vision-Language Guidance
by: Srivastava, Divyansh, et al.
Published: (2024)

Muon in Vision Transformers: Optimizer-Recipe Interactions and Gradient Spectra
by: Southworth, Ben S., et al.
Published: (2026)

Inside-Out: Measuring Generalization in Vision Transformers Through Inner Workings
by: Peng, Yunxiang, et al.
Published: (2026)

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

Riemannian Motion Generation: A Unified Framework for Human Motion Representation and Generation via Riemannian Flow Matching
by: Miao, Fangran, et al.
Published: (2026)

Unbiased Scene Graph Generation from Biased Training
by: Tang, Kaihua, et al.
Published: (2020)

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

Mixture of Distributions Matters: Dynamic Sparse Attention for Efficient Video Diffusion Transformers
by: Liu, Yuxi, et al.
Published: (2026)

Stable Vision Concept Transformers for Medical Diagnosis
by: Hu, Lijie, et al.
Published: (2025)

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