SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2109.09883 · ICCV · 2021

On the Importance of Distractors for Few-Shot Classification

Yu-Xiong Wang, José Moura, Rajshekhar Das

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

Few-shot classification aims at classifying categories of a novel task by learning from just a few (typically, 1 to 5) labelled examples. An effective approach to few-shot classification involves a prior model trained on a large-sample base domain, which is then finetuned over the novel fewshot task to yield generalizable representations. However, task-specific finetuning is prone to overfitting due to the lack of enough training examples. To alleviate this issue, we propose a new finetuning approach based on contrastive learning that reuses unlabelled examples from the base domain in the form of distractors. Unlike the nature of unlabelled data used in prior works, distractors belong to classes that do not overlap with the novel categories. We demonstrate for the first time that inclusion of such distractors can significantly boost few-shot generalization. Our technical novelty includes a stochastic pairing of examples sharing the same category in the few-shot task and a weighting term that controls the relative influence of taskspecific negatives and distractors. An important aspect of our finetuning objective is that it is agnostic to distractor labels and hence applicable to various base domain settings. More precisely, compared to state-of-the-art approaches, our method shows accuracy gains of up to 12% in crossdomain and up to 5% in unsupervised prior-learning settings. Our code is available at https://github.com/ quantacode/Contrastive-Finetuning.git

For agents

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

get_harvested_code_for_paper("2109.09883")
get_code_for_paper("2109.09883")
have("2109.09883")

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

curl https://syntology.ai/api/ran/2109.09883.json

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

[![Syntology run record](https://syntology.ai/api/ran/2109.09883.svg)](https://syntology.ai/paper/2109.09883)

Connect an agent — have() is free.