Model-Agnostic Meta-Learning for Multimodal Task Distributions
Gradient-based meta-learners such as MAML (Finn et al., 2017) are able to learn a meta-prior from similar tasks to adapt to novel tasks from the same distribution with few gradient updates. One important limitation of such frameworks is that they seek a common initialization shared across the entire task distribution, substantially limiting the diversity of the task distributions that they are able to learn from. In this paper, we augment MAML with the capability to identify tasks sampled from a multimodal task distribution and adapt quickly through gradient updates. Specifically, we propose a multimodal MAML algorithm that is able to modulate its meta-learned prior according to the identified task, allowing faster adaptation. We evaluate the proposed model on a diverse set of problems including regression, few-shot image classification, and reinforcement learning. The results demonstrate the effectiveness of our model in modulating the meta-learned prior in response to the characteristics of tasks sampled from a multimodal distribution.
Code (0)
등록된 구현이 없습니다.
Tasks
DiversityFew-Shot Image Classificationimage-classificationImage ClassificationMeta-LearningmodelSimilar Papers 제목 키워드 기반
Multimodal Model-Agnostic Meta-Learning via Task-Aware Modulation
Model-agnostic meta-learners aim to acquire meta-learned parameters from similar tasks to adapt to novel tasks from the same distribution with few gradient updates. With the flexibility in the choice of models, those fra…
Few-Shot Image ClassificationFew-Shot LearningGeneral Classificationimage-classification+5Toward Multimodal Model-Agnostic Meta-Learning
Gradient-based meta-learners such as MAML are able to learn a meta-prior from similar tasks to adapt to novel tasks from the same distribution with few gradient updates. One important limitation of such frameworks is tha…
DiversityFew-Shot Image Classificationimage-classificationImage Classification+3Revisit Multimodal Meta-Learning through the Lens of Multi-Task Learning
Multimodal meta-learning is a recent problem that extends conventional few-shot meta-learning by generalizing its setup to diverse multimodal task distributions. This setup makes a step towards mimicking how humans make …
Meta-LearningMulti-Task LearningTransfer LearningUncertainty-Aware Meta-Learning for Multimodal Task Distributions
Meta-learning or learning to learn is a popular approach for learning new tasks with limited data (i.e., few-shot learning) by leveraging the commonalities among different tasks. However, meta-learned models can perform …
Bayesian InferenceFew-Shot LearningMeta-LearningMetaRA: Metamorphic Robustness Assessment for Multimodal Large Language Model-based Visual Question Answering Systems
Visual Question Answering (VQA), as the representative multimodal task, serves as a key benchmark for evaluating the reasoning capabilities of Multimodal Large Language Models (MLLMs). However, existing evaluations large…
Visual Question AnsweringMultimodal Reasoning