SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1409.8403 · 2014

Evaluation of Output Embeddings for Fine-Grained Image Classification

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

Image classification has advanced significantly in recent years with the availability of large-scale image sets. However, fine-grained classification remains a major challenge due to the annotation cost of large numbers of fine-grained categories. This project shows that compelling classification performance can be achieved on such categories even without labeled training data. Given image and class embeddings, we learn a compatibility function such that matching embeddings are assigned a higher score than mismatching ones; zero-shot classification of an image proceeds by finding the label yielding the highest joint compatibility score. We use state-of-the-art image features and focus on different supervised attributes and unsupervised output embeddings either derived from hierarchies or learned from unlabeled text corpora. We establish a substantially improved state-of-the-art on the Animals with Attributes and Caltech-UCSD Birds datasets. Most encouragingly, we demonstrate that purely unsupervised output embeddings (learned from Wikipedia and improved with fine-grained text) achieve compelling results, even outperforming the previous supervised state-of-the-art. By combining different output embeddings, we further improve results.

For agents

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

get_harvested_code_for_paper("1409.8403")
get_code_for_paper("1409.8403")
have("1409.8403")

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

curl https://syntology.ai/api/ran/1409.8403.json

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

[![Syntology run record](https://syntology.ai/api/ran/1409.8403.svg)](https://syntology.ai/paper/1409.8403)

Connect an agent — have() is free.