SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2112.00725 · ICLR · 2023

CLASSES BY EXTRAPOLATING FROM A SINGLE IMAGE

Yuki Asano, Aaqib Saeed

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

Extrapolating from one image. Strongly augmented patches from a single image are used to train a student (S) to distinguish semantic classes, such as those in ImageNet. The student neural network is initialized randomly and learns from a pretrained teacher (T) via KL-divergence. Although almost none of target categories are present in the image, we find student performances of > 69% for classifying ImageNet's 1000 classes. In this paper, we develop this single datum learning framework and investigate it across datasets and domains.

For agents

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

get_harvested_code_for_paper("2112.00725")
get_code_for_paper("2112.00725")
have("2112.00725")

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

curl https://syntology.ai/api/ran/2112.00725.json

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

[![Syntology run record](https://syntology.ai/api/ran/2112.00725.svg)](https://syntology.ai/paper/2112.00725)

Connect an agent — have() is free.