pith. sign in

arxiv: 2011.09066 · v1 · pith:7GUZ3ABAnew · submitted 2020-11-18 · 💻 cs.CV

Shaping Deep Feature Space towards Gaussian Mixture for Visual Classification

classification 💻 cs.CV
keywords lossclassificationfeaturedeepadversarialgaussianmixturemodels
0
0 comments X
read the original abstract

The softmax cross-entropy loss function has been widely used to train deep models for various tasks. In this work, we propose a Gaussian mixture (GM) loss function for deep neural networks for visual classification. Unlike the softmax cross-entropy loss, our method explicitly shapes the deep feature space towards a Gaussian Mixture distribution. With a classification margin and a likelihood regularization, the GM loss facilitates both high classification performance and accurate modeling of the feature distribution. The GM loss can be readily used to distinguish abnormal inputs, such as the adversarial examples, based on the discrepancy between feature distributions of the inputs and the training set. Furthermore, theoretical analysis shows that a symmetric feature space can be achieved by using the GM loss, which enables the models to perform robustly against adversarial attacks. The proposed model can be implemented easily and efficiently without using extra trainable parameters. Extensive evaluations demonstrate that the proposed method performs favorably not only on image classification but also on robust detection of adversarial examples generated by strong attacks under different threat models.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Amortized Probabilistic Retrieval of Atmospheric CO2 from OCO-2 Spectra Using Deep Learning with Laplace Approximations and Normalizing Flows

    cs.LG 2026-06 unverdicted novelty 6.0

    A deep learning method amortizes probabilistic XCO2 retrieval from OCO-2 spectra via Laplace approximations and normalizing flows, trained on simulations with model errors to achieve faster inference and better-calibr...

  2. Scalable generative modeling of non-Gaussian spatio-temporal fields via autoregressive Gaussian processes

    stat.ME 2026-05 unverdicted novelty 6.0

    An autoregressive Gaussian process transport-map construction factors spatio-temporal joint densities into conditional distributions with data-dependent sparsity to enable scalable generative modeling of non-Gaussian fields.