ReMarNet: Conjoint Relation and Margin Learning for Small-Sample Image Classification

TL;DR

ReMarNet introduces a dual-network approach combining relation-based and margin-based learning to improve discriminative feature extraction in small-sample image classification, achieving competitive results.

Contribution

It proposes a novel neural network architecture that integrates relation and margin learning mechanisms for better small-sample classification performance.

Findings

Effective in learning discriminative features from limited data

Achieves competitive performance against state-of-the-art methods

Demonstrates robustness across four image datasets

Abstract

Despite achieving state-of-the-art performance, deep learning methods generally require a large amount of labeled data during training and may suffer from overfitting when the sample size is small. To ensure good generalizability of deep networks under small sample sizes, learning discriminative features is crucial. To this end, several loss functions have been proposed to encourage large intra-class compactness and inter-class separability. In this paper, we propose to enhance the discriminative power of features from a new perspective by introducing a novel neural network termed Relation-and-Margin learning Network (ReMarNet). Our method assembles two networks of different backbones so as to learn the features that can perform excellently in both of the aforementioned two classification mechanisms. Specifically, a relation network is used to learn the features that can support classification based on the similarity between a sample and a class prototype; at the meantime, a fully connected network with the cross entropy loss is used for classification via the decision boundary. Experiments on four image datasets demonstrate that our approach is effective in learning discriminative features from a small set of labeled samples and achieves competitive performance against state-of-the-art methods. Codes are available at https://github.com/liyunyu08/ReMarNet.