94 papers with code • 65 benchmarks • 17 datasets
Few-shot image classification is the task of doing image classification with only a few examples for each category (typically < 6 examples).
( Image credit: Learning Embedding Adaptation for Few-Shot Learning )
If this is not done, the meta-learner can ignore the task training data and learn a single model that performs all of the meta-training tasks zero-shot, but does not adapt effectively to new image classes.
We propose an algorithm for meta-learning that is model-agnostic, in the sense that it is compatible with any model trained with gradient descent and applicable to a variety of different learning problems, including classification, regression, and reinforcement learning.
We conclude with a discussion of the rapid learning vs feature reuse question for meta-learning algorithms more broadly.
This paper considers meta-learning problems, where there is a distribution of tasks, and we would like to obtain an agent that performs well (i. e., learns quickly) when presented with a previously unseen task sampled from this distribution.
We propose prototypical networks for the problem of few-shot classification, where a classifier must generalize to new classes not seen in the training set, given only a small number of examples of each new class.
Once trained, a RN is able to classify images of new classes by computing relation scores between query images and the few examples of each new class without further updating the network.
Few-shot classification aims to learn a classifier to recognize unseen classes during training with limited labeled examples.
Our algorithm improves one-shot accuracy on ImageNet from 87. 6% to 93. 2% and from 88. 0% to 93. 8% on Omniglot compared to competing approaches.
We introduce a conditional neural process based approach to the multi-task classification setting for this purpose, and establish connections to the meta-learning and few-shot learning literature.
Ranked #6 on Few-Shot Image Classification on Meta-Dataset Rank