Multimodal Model-Agnostic Meta-Learning via Task-Aware Modulation
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019), pp. 1-12, 2019.
image classificationreinforcement learningmultimodal distribution
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 frameworks demonstrate appealing performance on a variety of domains such as few-shot image classification and reinforcemen...More
PPT (Upload PPT)