SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2207.10225 · ECCV · 2022

On Label Granularity and Object Localization

Serge Belongie, Pietro Perona, Elijah Cole, Grant Horn, Oisin Aodha, Xuan Yang, Andrew Howard, Kimberly Wilber, Marco Fornoni

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

Weakly supervised object localization (WSOL) aims to learn representations that encode object location using only image-level category labels. However, many objects can be labeled at different levels of granularity. Is it an animal, a bird, or a great horned owl? Which image-level labels should we use? In this paper we study the role of label granularity in WSOL. To facilitate this investigation we introduce iNat-Loc500, a new large-scale fine-grained benchmark dataset for WSOL. Surprisingly, we find that choosing the right training label granularity provides a much larger performance boost than choosing the best WSOL algorithm. We also show that changing the label granularity can significantly improve data efficiency.

For agents

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

get_harvested_code_for_paper("2207.10225")
get_code_for_paper("2207.10225")
have("2207.10225")

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

curl https://syntology.ai/api/ran/2207.10225.json

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

[![Syntology run record](https://syntology.ai/api/ran/2207.10225.svg)](https://syntology.ai/paper/2207.10225)

Connect an agent — have() is free.