Handling previously unseen tasks after given only a few training examples continues to be a tough challenge in machine learning. We propose TapNets, neural networks augmented with task-adaptive projection for improved few-shot learning. Here, employing a meta-learning strategy with episode-based training, a network and a set of per-class reference vectors are learned across widely varying tasks. At the same time, for every episode, features in the embedding space are linearly projected into a new space as a form of quick task-specific conditioning. The training loss is obtained based on a distance metric between the query and the reference vectors in the projection space. Excellent generalization results in this way. When tested on the Omniglot, miniImageNet and tieredImageNet datasets, we obtain state of the art classification accuracies under various few-shot scenarios.
Sung Whan Yoon (Korea Advanced Institute of Science and Technology (KAIST))
I am currently a postdoctoral researcher in Korea Advanced Institute of Science and Technology (KAIST) from Sep. 2017. I received my Ph.D. in School of Electrical Engineering from KAIST, in Aug. 2017, where I was advised by Prof. Jaekyun Moon. My research interests are in the area of artificial intelligence, distributed system and information/coding theory with emphasis on error-correction codes, distributed resources in future networks and efficient learning algorithm of neural networks. Recently, I'm dedicated to meta-learning algorithms with balanced inductive bias and adaptation for efficient few-shot classification. In broad sense, I hope to develop an intelligent system built on efficient learning algorithms with following features: being able to learn from big data (even noisy and non-annotated), leveraging distributed resources (storage, computation and communication) and being hardware-friendly.
Jun Seo (Korea Advanced Institute of Science and Technology(KAIST))
Jaekyun Moon (KAIST)
Related Events (a corresponding poster, oral, or spotlight)
2019 Oral: TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learning »
Tue Jun 11th 11:30 -- 11:35 AM Room Hall A