HyperSpaceX: Radial and Angular Exploration of HyperSpherical Dimensions

TL;DR

HyperSpaceX introduces a novel approach that explores both angular and radial features in hyperspherical spaces, significantly improving class discrimination and achieving state-of-the-art results in object classification and face recognition tasks.

Contribution

It proposes HyperSpaceX with DistArc loss to enhance feature discriminability by exploring multi-radial and angular dimensions in hyperspherical spaces, a novel extension over traditional angular-only methods.

Findings

Achieves up to 20% performance improvement on large-scale object datasets.

Attains up to 6% gain in face recognition accuracy.

Demonstrates state-of-the-art results across multiple datasets.

Abstract

Traditional deep learning models rely on methods such as softmax cross-entropy and ArcFace loss for tasks like classification and face recognition. These methods mainly explore angular features in a hyperspherical space, often resulting in entangled inter-class features due to dense angular data across many classes. In this paper, a new field of feature exploration is proposed known as HyperSpaceX which enhances class discrimination by exploring both angular and radial dimensions in multi-hyperspherical spaces, facilitated by a novel DistArc loss. The proposed DistArc loss encompasses three feature arrangement components: two angular and one radial, enforcing intra-class binding and inter-class separation in multi-radial arrangement, improving feature discriminability. Evaluation of HyperSpaceX framework for the novel representation utilizes a proposed predictive measure that accounts for both angular and radial elements, providing a more comprehensive assessment of model accuracy beyond standard metrics. Experiments across seven object classification and six face recognition datasets demonstrate state-of-the-art (SoTA) results obtained from HyperSpaceX, achieving up to a 20% performance improvement on large-scale object datasets in lower dimensions and up to 6% gain in higher dimensions.