krisorn kachai

In this paper we propose a novel few-shot learning method called meta-transfer learning (MTL) which learns to adapt a deep NN for few shot learning tasks. Specifically, "meta" refers to training multiple tasks, and "transfer" is achieved by learning scaling and shifting functions of DNN weights for each task.

In this paper, we propose Transductive Propagation Network (TPN), a novel meta-learning framework for transductive inference that classifies the entire test set at once to alleviate the low-data problem. Specifically, we propose to learn to propagate labels from labeled instances to unlabeled test instances.

This project shows that compelling classification performance can be achieved on such categories even without labeled training data.

Zero-shot learning (ZSL) is a model's ability to detect classes never seen during training. The condition is that the classes are not known during supervised learning.

The Fine-Grained Image Classification task focuses on differentiating between hard-to-distinguish object classes, such as species of birds, flowers, or animals; and identifying the makes or models of vehicles.

In this work, we develop methods for few-shot image classification from a new perspective of optimal matching between image regions. We employ the Earth Mover's Distance (EMD) as a metric to compute a structural distance between dense image representations to determine image relevance.

Image retrieval systems aim to find similar images to a query image among an image dataset.

Harnessing the Power of Infinitely Wide Deep Nets on Small-data Tasks

Subfield of machine learning

Subfield of machine learning.Transfer learning is a methodology where weights from a model trained on one task are taken and either used (a) to construct a fixed feature extractor, (b) as weight initialization and/or fine-tuning.

Supervised image classification with tens to hundreds of labeled training examples.

TextCaps : Handwritten Character Recognition with Very Small Datasets

In this work, we identify that metric scaling and metric task conditioning are important to improve the performance of few-shot algorithms. Our analysis reveals that simple metric scaling completely changes the nature of few-shot algorithm parameter updates.