Data Augmentation for Meta-Learning
Conventional image classifiers are trained by randomly sampling mini-batches of images. To achieve state-of-the-art performance, practitioners use sophisticated data augmentation schemes to expand the amount of training data available for sampling. In contrast, meta-learning algorithms sample support data, query data, and tasks on each training step. In this complex sampling scenario, data augmentation can be used not only to expand the number of images available per class, but also to generate entirely new classes/tasks. We systematically dissect the meta-learning pipeline and investigate the distinct ways in which data augmentation can be integrated at both the image and class levels. Our proposed meta-specific data augmentation significantly improves the performance of meta-learners on few-shot classification benchmarks.
Code (1)
Tasks
Data AugmentationMeta-LearningSimilar Papers 제목 키워드 기반
Meta-Learning Requires Meta-Augmentation
Meta-learning algorithms aim to learn two components: a model that predicts targets for a task, and a base learner that quickly updates that model when given examples from a new task. This additional level of learning ca…
Meta-LearningSet-based Meta-Interpolation for Few-Task Meta-Learning
Meta-learning approaches enable machine learning systems to adapt to new tasks given few examples by leveraging knowledge from related tasks. However, a large number of meta-training tasks are still required for generali…
Bilevel Optimizationimage-classificationImage ClassificationMeta-Learning+5MetaTPT: Meta Test-time Prompt Tuning for Vision-Language Models
Vision-language models (VLMs) such as CLIP exhibit strong zero-shot generalization but remain sensitive to domain shifts at test time. Test-time prompt tuning (TPT) mitigates this issue by adapting prompts with fixed aug…
Zero-shot GeneralizationDomain GeneralizationTest-time AdaptationRobust Self-Augmentation for Named Entity Recognition with Meta Reweighting
Self-augmentation has received increasing research interest recently to improve named entity recognition (NER) performance in low-resource scenarios. Token substitution and mixup are two feasible heterogeneous self-augme…
named-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)NERTask Augmentation by Rotating for Meta-Learning
Data augmentation is one of the most effective approaches for improving the accuracy of modern machine learning models, and it is also indispensable to train a deep model for meta-learning. In this paper, we introduce a …
Data AugmentationFew-Shot LearningMeta-Learning