SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2007.03047 · 2020

Leveraging Class Hierarchies with Metric-Guided Prototype 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. 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

In many classification tasks, the set of target classes can be organized into a hierarchy. This structure induces a semantic distance between classes, and can be summarised under the form of a cost matrix, which defines a finite metric on the class set. In this paper, we propose to model the hierarchical class structure by integrating this metric in the supervision of a prototypical network. Our method relies on jointly learning a feature-extracting network and a set of class prototypes whose relative arrangement in the embedding space follows an hierarchical metric. We show that this approach allows for a consistent improvement of the error rate weighted by the cost matrix when compared to traditional methods and other prototype-based strategies. Furthermore, when the induced metric contains insight on the data structure, our method improves the overall precision as well. Experiments on four different public datasets - from agricultural time series classification to depth image semantic segmentation - validate our approach.

For agents

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

get_harvested_code_for_paper("2007.03047")
get_code_for_paper("2007.03047")
have("2007.03047")

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

curl https://syntology.ai/api/ran/2007.03047.json

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

[![Syntology run record](https://syntology.ai/api/ran/2007.03047.svg)](https://syntology.ai/paper/2007.03047)

Connect an agent — have() is free.