SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2008.02465 · 2020

Few-shot Classification via Adaptive Attention

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

Training a neural network model that can quickly adapt to a new task is highly desirable yet challenging for few-shot learning problems. Recent few-shot learning methods mostly concentrate on developing various meta-learning strategies from two aspects, namely optimizing an initial model or learning a distance metric. In this work, we propose a novel few-shot learning method via optimizing and fast adapting the query sample representation based on very few reference samples. To be specific, we devise a simple and efficient meta-reweighting strategy to adapt the sample representations and generate soft attention to refine the representation such that the relevant features from the query and support samples can be extracted for a better few-shot classification. Such an adaptive attention model is also able to explain what the classification model is looking for as the evidence for classification to some extent. As demonstrated experimentally, the proposed model achieves state-of-the-art classification results on various benchmark few-shot classification and fine-grained recognition datasets.

For agents

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

get_harvested_code_for_paper("2008.02465")
get_code_for_paper("2008.02465")
have("2008.02465")

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

curl https://syntology.ai/api/ran/2008.02465.json

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

[![Syntology run record](https://syntology.ai/api/ran/2008.02465.svg)](https://syntology.ai/paper/2008.02465)

Connect an agent — have() is free.