SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2106.10846 · 2021

Trainable Class Prototypes for Few-Shot Learning

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. We have no repository linked to it either. That is a statement about our graph, not about the paper.

Abstract

Metric learning is a widely used method for few shot learning in which the quality of prototypes plays a key role in the algorithm. In this paper we propose the trainable prototypes for distance measure instead of the artificial ones within the meta-training and task-training framework. Also to avoid the disadvantages that the episodic meta-training brought, we adopt non-episodic meta-training based on self-supervised learning. Overall we solve the few-shot tasks in two phases: meta-training a transferable feature extractor via self-supervised learning and training the prototypes for metric classification. In addition, the simple attention mechanism is used in both meta-training and task-training. Our method achieves state-of-the-art performance in a variety of established few-shot tasks on the standard few-shot visual classification dataset, with about 20% increase compared to the available unsupervised few-shot learning methods.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2106.10846")
get_code_for_paper("2106.10846")
have("2106.10846")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2106.10846.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2106.10846.svg)](https://syntology.ai/paper/2106.10846)

Connect an agent — have() is free.