SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1607.07262 · 2016

Automatic Attribute Discovery with Neural Activations

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

How can a machine learn to recognize visual attributes emerging out of online community without a definitive supervised dataset? This paper proposes an automatic approach to discover and analyze visual attributes from a noisy collection of image-text data on the Web. Our approach is based on the relationship between attributes and neural activations in the deep network. We characterize the visual property of the attribute word as a divergence within weakly-annotated set of images. We show that the neural activations are useful for discovering and learning a classifier that well agrees with human perception from the noisy real-world Web data. The empirical study suggests the layered structure of the deep neural networks also gives us insights into the perceptual depth of the given word. Finally, we demonstrate that we can utilize highly-activating neurons for finding semantically relevant regions.

For agents

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

get_harvested_code_for_paper("1607.07262")
get_code_for_paper("1607.07262")
have("1607.07262")

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

curl https://syntology.ai/api/ran/1607.07262.json

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

[![Syntology run record](https://syntology.ai/api/ran/1607.07262.svg)](https://syntology.ai/paper/1607.07262)

Connect an agent — have() is free.