paper-with-me

Papers

MetaAugment: Sample-Aware Data Augmentation Policy Learning

2020-12-22 · Fengwei Zhou, Jiawei Li, Chuanlong Xie, Fei Chen, Lanqing Hong, Rui Sun, Zhenguo Li

Automated data augmentation has shown superior performance in image recognition. Existing works search for dataset-level augmentation policies without considering individual sample variations, which are likely to be sub-optimal. On the other hand, learning different policies for different samples naively could greatly increase the computing cost. In this paper, we learn a sample-aware data augmentation policy efficiently by formulating it as a sample reweighting problem. Specifically, an augmentation policy network takes a transformation and the corresponding augmented image as inputs, and outputs a weight to adjust the augmented image loss computed by a task network. At training stage, the task network minimizes the weighted losses of augmented training images, while the policy network minimizes the loss of the task network on a validation set via meta-learning. We theoretically prove the convergence of the training procedure and further derive the exact convergence rate. Superior performance is achieved on widely-used benchmarks including CIFAR-10/100, Omniglot, and ImageNet.

📄 PDF Abstract BibTeX arXiv:2012.12076

Code (0)

등록된 구현이 없습니다.

Tasks

Data AugmentationMeta-Learning

Similar Papers 제목 키워드 기반

LA3: Efficient Label-Aware AutoAugment

2023-04-20 · Mingjun Zhao, Shan Lu, Zixuan Wang, Xiaoli Wang 외

Automated augmentation is an emerging and effective technique to search for data augmentation policies to improve generalizability of deep neural network training. Most existing work focuses on constructing a unified pol…

Bayesian OptimizationData Augmentation

Sample-aware RandAugment: Search-free Automatic Data Augmentation for Effective Image Recognition

2025-08-11 · Anqi Xiao, Weichen Yu, Hongyuan Yu arxiv

Automatic data augmentation (AutoDA) plays an important role in enhancing the generalization of neural networks. However, mainstream AutoDA methods often encounter two challenges: either the search process is excessively…

Data AugmentationObject Detection

Improving Generalization in Visual Reinforcement Learning via Conflict-aware Gradient Agreement Augmentation

2023-08-02 · ICCV 2023 1 · Siao Liu, Zhaoyu Chen, Yang Liu, Yuzheng Wang 외

Learning a policy with great generalization to unseen environments remains challenging but critical in visual reinforcement learning. Despite the success of augmentation combination in the supervised learning generalizat…

reinforcement-learning

SapAugment: Learning A Sample Adaptive Policy for Data Augmentation

2020-11-02 · Ting-yao Hu, Ashish Shrivastava, Jen-Hao Rick Chang, Hema Koppula 외

Data augmentation methods usually apply the same augmentation (or a mix of them) to all the training samples. For example, to perturb data with noise, the noise is sampled from a Normal distribution with a fixed standard…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Data Augmentationspeech-recognition+1

HeaPA: Difficulty-Aware Heap Sampling and On-Policy Query Augmentation for LLM Reinforcement Learning

2026-01-30 · Weiqi Wang, Xin Liu, Binxuan Huang, Hejie Cui 외 arxiv

RLVR has become a standard recipe for training LLMs on reasoning tasks with verifiable outcomes, but when rollout generation dominates the cost, efficiency hinges on which prompts are sampled and when. In practice, promp…

Reinforcement Learning