SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2107.07746 · NeurIPS · 2021

Rectifying the Shortcut Learning of Background for Few-Shot Learning

Liangjian Wen, Zenglin Xu, Qi Tian, Lingxi Xie, Xu Luo, Longhui Wei, Jinrong Yang

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

The category gap between training and evaluation has been characterised as one of the main obstacles to the success of Few-Shot Learning (FSL). In this paper, we for the first time empirically identify image background, common in realistic images, as a shortcut knowledge helpful for in-class classification but ungeneralizable beyond training categories in FSL. A novel framework, COSOC, is designed to tackle this problem by extracting foreground objects in images at both training and evaluation without any extra supervision. Extensive experiments carried on inductive FSL tasks demonstrate the effectiveness of our approaches.

For agents

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

get_harvested_code_for_paper("2107.07746")
get_code_for_paper("2107.07746")
have("2107.07746")

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

curl https://syntology.ai/api/ran/2107.07746.json

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

[![Syntology run record](https://syntology.ai/api/ran/2107.07746.svg)](https://syntology.ai/paper/2107.07746)

Connect an agent — have() is free.