Cover Image

Towards Understanding Why Data Augmentation Improves Generalization

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Jingyang, Pan, Jiachun, Toh, Kim-Chuan, Zhou, Pan
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Memory-Efficient 4-bit Preconditioned Stochastic Optimization
by: Li, Jingyang, et al.
Published: (2024)

Towards Understanding Why FixMatch Generalizes Better Than Supervised Learning
by: Li, Jingyang, et al.
Published: (2024)

Enhancing Long Video Generation Consistency without Tuning
by: Li, Xingyao, et al.
Published: (2024)

Generative Spatiotemporal Data Augmentation
by: Zhou, Jinfan, et al.
Published: (2025)

ScribbleGen: Generative Data Augmentation Improves Scribble-supervised Semantic Segmentation
by: Schnell, Jacob, et al.
Published: (2023)

Consistent3D: Towards Consistent High-Fidelity Text-to-3D Generation with Deterministic Sampling Prior
by: Wu, Zike, et al.
Published: (2024)

Understanding the Detrimental Class-level Effects of Data Augmentation
by: Kirichenko, Polina, et al.
Published: (2023)

Effective and Efficient Masked Image Generation Models
by: You, Zebin, et al.
Published: (2025)

GeoMix: Towards Geometry-Aware Data Augmentation
by: Zhao, Wentao, et al.
Published: (2024)

Diffusion-based Data Augmentation and Knowledge Distillation with Generated Soft Labels Solving Data Scarcity Problems of SAR Oil Spill Segmentation
by: Moon, Jaeho, et al.
Published: (2024)

Data Augmentation For Small Object using Fast AutoAugment
by: Yoon, DaeEun, et al.
Published: (2025)

AutoDFP: Automatic Data-Free Pruning via Channel Similarity Reconstruction
by: Li, Siqi, et al.
Published: (2024)

Privacy-Preserving Debiasing using Data Augmentation and Machine Unlearning
by: Pan, Zhixin, et al.
Published: (2024)

Improving Consistency Models with Generator-Augmented Flows
by: Issenhuth, Thibaut, et al.
Published: (2024)

DragDiffusion: Harnessing Diffusion Models for Interactive Point-based Image Editing
by: Shi, Yujun, et al.
Published: (2023)

AdjointDPM: Adjoint Sensitivity Method for Gradient Backpropagation of Diffusion Probabilistic Models
by: Pan, Jiachun, et al.
Published: (2023)

Improved Multi-Task Brain Tumour Segmentation with Synthetic Data Augmentation
by: Ferreira, André, et al.
Published: (2024)

Learning with Open-world Noisy Data via Class-independent Margin in Dual Representation Space
by: Pan, Linchao, et al.
Published: (2025)

Learning from the Unseen: Generative Data Augmentation for Geometric-Semantic Accident Anticipation
by: Guan, Yanchen, et al.
Published: (2026)

Learning From Design Procedure To Generate CAD Programs for Data Augmentation
by: Chen, Yan-Ying, et al.
Published: (2026)

Why Does RL Generalize Better Than SFT? A Data-Centric Perspective on VLM Post-Training
by: Lu, Aojun, et al.
Published: (2026)

Towards Understanding Why Label Smoothing Degrades Selective Classification and How to Fix It
by: Xia, Guoxuan, et al.
Published: (2024)

Towards Sparse Video Understanding and Reasoning
by: Xu, Chenwei, et al.
Published: (2026)

Analyzing Effects of Mixed Sample Data Augmentation on Model Interpretability
by: Won, Soyoun, et al.
Published: (2023)

Why Does Little Robustness Help? A Further Step Towards Understanding Adversarial Transferability
by: Zhang, Yechao, et al.
Published: (2023)

Retrieval-Augmented Gaussian Avatars: Improving Expression Generalization
by: Levy, Matan, et al.
Published: (2026)

HandCraft: Dynamic Sign Generation for Synthetic Data Augmentation
by: Rios, Gaston Gustavo, et al.
Published: (2025)

LatentUM: Unleashing the Potential of Interleaved Cross-Modal Reasoning via a Latent-Space Unified Model
by: Jin, Jiachun, et al.
Published: (2026)

Towards Understanding Adversarial Transferability in Federated Learning
by: Li, Yijiang, et al.
Published: (2023)

Retrieval-Augmented Score Distillation for Text-to-3D Generation
by: Seo, Junyoung, et al.
Published: (2024)

Improving Personalisation in Valence and Arousal Prediction using Data Augmentation
by: Nwadike, Munachiso, et al.
Published: (2024)

Bridging the Semantic Gaps: Improving Medical VQA Consistency with LLM-Augmented Question Sets
by: Ma, Yongpei, et al.
Published: (2025)

Stable Consistency Tuning: Understanding and Improving Consistency Models
by: Wang, Fu-Yun, et al.
Published: (2024)

Improving Adversarial Transferability via Model Alignment
by: Ma, Avery, et al.
Published: (2023)

Scaling-based Data Augmentation for Generative Models and its Theoretical Extension
by: Koike, Yoshitaka, et al.
Published: (2024)

Towards Understanding the Working Mechanism of Text-to-Image Diffusion Model
by: Yi, Mingyang, et al.
Published: (2024)

LPT++: Efficient Training on Mixture of Long-tailed Experts
by: Dong, Bowen, et al.
Published: (2024)

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

Multi-Modal Data-Efficient 3D Scene Understanding for Autonomous Driving
by: Kong, Lingdong, et al.
Published: (2024)

GraphTARIF: Linear Graph Transformer with Augmented Rank and Improved Focus
by: Hu, Zhaolin, et al.
Published: (2025)