HyperSpaceX: Radial and Angular Exploration of HyperSpherical Dimensions

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Chiranjeev, Chiranjeev, Dosi, Muskan, Thakral, Kartik, Vatsa, Mayank, Singh, Richa
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914900733853696
author Chiranjeev, Chiranjeev
Dosi, Muskan
Thakral, Kartik
Vatsa, Mayank
Singh, Richa
author_facet Chiranjeev, Chiranjeev
Dosi, Muskan
Thakral, Kartik
Vatsa, Mayank
Singh, Richa
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2408_02494
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle HyperSpaceX: Radial and Angular Exploration of HyperSpherical Dimensions
Chiranjeev, Chiranjeev
Dosi, Muskan
Thakral, Kartik
Vatsa, Mayank
Singh, Richa
Computer Vision and Pattern Recognition
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.
title HyperSpaceX: Radial and Angular Exploration of HyperSpherical Dimensions
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2408.02494