SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1801.05401 · 2018

Low-Shot Learning from Imaginary Data

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. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Humans can quickly learn new visual concepts, perhaps because they can easily visualize or imagine what novel objects look like from different views. Incorporating this ability to hallucinate novel instances of new concepts might help machine vision systems perform better low-shot learning, i.e., learning concepts from few examples. We present a novel approach to low-shot learning that uses this idea. Our approach builds on recent progress in meta-learning ("learning to learn") by combining a meta-learner with a "hallucinator" that produces additional training examples, and optimizing both models jointly. Our hallucinator can be incorporated into a variety of meta-learners and provides significant gains: up to a 6 point boost in classification accuracy when only a single training example is available, yielding state-of-the-art performance on the challenging ImageNet low-shot classification benchmark.

For agents

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

get_harvested_code_for_paper("1801.05401")
get_code_for_paper("1801.05401")
have("1801.05401")

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

curl https://syntology.ai/api/ran/1801.05401.json

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

[![Syntology run record](https://syntology.ai/api/ran/1801.05401.svg)](https://syntology.ai/paper/1801.05401)

Connect an agent — have() is free.