Self-guided information for few-shot classification *

doi:10.1016/j.patcog.2022.108880

Self-guided information for few-shot classification *

2022-11-01

14

PRE

AI

DOI：10.1016/j.patcog.2022.108880

Original

Original request for help

Save

Abstract

En 中文

Few-shot classification aims to identify novel categories using only a few labeled samples. Generally, the metric-based few-shot classification methods compare the feature embedding of Query samples (unla-beled samples) with Support samples (labeled samples) in a metric algorithm to predict which category the Query sample belongs to. Obtaining a good feature embedding for each sample in the feature extrac-tion stage can improve the classification accuracy in the metric stage. Based on this, we design the Self -Guided Information Convolution (SGI-Conv), an improved convolution structure, which utilizes the high-level features to guide the network to extract the required discriminative features. To effectively utilize the feature embeddings of samples, we divide the metric network into multiple blocks and build a multi -layer graph convolutional network by sharing adjacent matrices. The multi-layer structure enhances the aggregation ability of graph convolution. Extensive experiments on multiple benchmark datasets demon-strate that our method has achieved competitive results on the few-shot classification tasks.(c) 2022 Elsevier Ltd. All rights reserved.

Keywords:

Few-shot classification

Graph convolution network

Self-guided information

Self-guided information for few-shot classification *

Abstract

Journal

Organization