MetaAugment: Sample-Aware Data Augmentation Policy Learning
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Data AugmentationMeta-LearningSimilar Papers 제목 키워드 기반
LA3: Efficient Label-Aware AutoAugment
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 AugmentationSample-aware RandAugment: Search-free Automatic Data Augmentation for Effective Image Recognition
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 DetectionImproving Generalization in Visual Reinforcement Learning via Conflict-aware Gradient Agreement Augmentation
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-learningSapAugment: Learning A Sample Adaptive Policy for Data Augmentation
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+1HeaPA: Difficulty-Aware Heap Sampling and On-Policy Query Augmentation for LLM Reinforcement Learning
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