HASeparator: Hyperplane-Assisted Softmax

TL;DR

This paper introduces HASeparator, a novel hyperplane-based method for CNN feature learning that improves class discrimination and intra-class compactness, outperforming traditional center-based schemes on image classification benchmarks.

Contribution

The paper proposes the Hyperplane-Assisted Softmax separator, a new class separation approach that enhances discrimination in CNN feature learning.

Findings

Demonstrates superior discrimination on image classification benchmarks

Outperforms traditional class center separation schemes

Improves intra-class compactness

Abstract

Efficient feature learning with Convolutional Neural Networks (CNNs) constitutes an increasingly imperative property since several challenging tasks of computer vision tend to require cascade schemes and modalities fusion. Feature learning aims at CNN models capable of extracting embeddings, exhibiting high discrimination among the different classes, as well as intra-class compactness. In this paper, a novel approach is introduced that has separator, which focuses on an effective hyperplane-based segregation of the classes instead of the common class centers separation scheme. Accordingly, an innovatory separator, namely the Hyperplane-Assisted Softmax separator (HASeparator), is proposed that demonstrates superior discrimination capabilities, as evaluated on popular image classification benchmarks.