paper-with-me

Papers

Enabling Data Diversity: Efficient Automatic Augmentation via Regularized Adversarial Training

2021-03-30 · Yunhe Gao, Zhiqiang Tang, Mu Zhou, Dimitris Metaxas

Data augmentation has proved extremely useful by increasing training data variance to alleviate overfitting and improve deep neural networks' generalization performance. In medical image analysis, a well-designed augmentation policy usually requires much expert knowledge and is difficult to generalize to multiple tasks due to the vast discrepancies among pixel intensities, image appearances, and object shapes in different medical tasks. To automate medical data augmentation, we propose a regularized adversarial training framework via two min-max objectives and three differentiable augmentation models covering affine transformation, deformation, and appearance changes. Our method is more automatic and efficient than previous automatic augmentation methods, which still rely on pre-defined operations with human-specified ranges and costly bi-level optimization. Extensive experiments demonstrated that our approach, with less training overhead, achieves superior performance over state-of-the-art auto-augmentation methods on both tasks of 2D skin cancer classification and 3D organs-at-risk segmentation.

📄 PDF Abstract BibTeX arXiv:2103.16493

Code (1)

yhygao/Efficient_Data_Augmentation 공식 구현

Tasks

Cancer ClassificationData AugmentationDiversityMedical Image AnalysisSkin Cancer Classification

Similar Papers 제목 키워드 기반

Virtual Data Augmentation: A Robust and General Framework for Fine-tuning Pre-trained Models

2021-09-13 · EMNLP 2021 11 · Kun Zhou, Wayne Xin Zhao, Sirui Wang, Fuzheng Zhang 외

Recent works have shown that powerful pre-trained language models (PLM) can be fooled by small perturbations or intentional attacks. To solve this issue, various data augmentation techniques are proposed to improve the r…

Data AugmentationDiversityLanguage ModelingLanguage Modelling

Adaptive Divergence Regularized Policy Optimization for Fine-tuning Generative Models

2025-10-20 · Jiajun Fan, Tong Wei, Chaoran Cheng, Yuxin Chen 외 arxiv

Balancing exploration and exploitation during reinforcement learning fine-tuning of generative models presents a critical challenge, as existing approaches rely on fixed divergence regularization that creates an inherent…

Text-to-Image GenerationReinforcement LearningStyle Transfer

DivAug: Plug-in Automated Data Augmentation with Explicit Diversity Maximization

2021-03-26 · ICCV 2021 10 · Zirui Liu, Haifeng Jin, Ting-Hsiang Wang, Kaixiong Zhou 외

Human-designed data augmentation strategies have been replaced by automatically learned augmentation policy in the past two years. Specifically, recent work has empirically shown that the superior performance of the auto…

Data AugmentationDiversity

Fully Automatic Video Colorization with Self-Regularization and Diversity

2019-08-04 · CVPR 2019 6 · Chenyang Lei, Qifeng Chen

We present a fully automatic approach to video colorization with self-regularization and diversity. Our model contains a colorization network for video frame colorization and a refinement network for spatiotemporal color…

ColorizationDiversity

Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels

2020-04-28 · ICLR 2021 1 · Ilya Kostrikov, Denis Yarats, Rob Fergus

We propose a simple data augmentation technique that can be applied to standard model-free reinforcement learning algorithms, enabling robust learning directly from pixels without the need for auxiliary losses or pre-tra…

AllAtari Games 100kContinuous ControlContrastive Learning+6