paper-with-me

Papers

Empirical Evidence for Simply Connected Decision Regions in Image Classifiers

2026-05-07 · Arjhun Swaminathan, Mete Akgün arxiv

Understanding the topology of decision regions is central to explaining the inner workings of deep neural networks. Prior empirical work has provided evidence that these regions are path connected. We study a stronger topological question: whether closed loops inside a decision region can be contracted without leaving that region. To this end, we propose an iterative quad-mesh filling procedure that constructs a finite-resolution label-preserving surface bounded by a given loop and lying entirely within the same decision region. We further connect this construction to natural Coons patches in order to quantify its deviation from a canonical geometric interpolation of the loop. By evaluating our method across several modern image-classification models, we provide empirical evidence supporting the hypothesis that decision regions in deep neural networks are not only path connected, but also simply connected.

📄 PDF Abstract BibTeX arXiv:2605.06380

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Data Interpolations in Deep Generative Models under Non-Simply-Connected Manifold Topology

2019-01-20 · Jiseob Kim, Byoung-Tak Zhang

Exploiting the deep generative model's remarkable ability of learning the data-manifold structure, some recent researches proposed a geometric data interpolation method based on the geodesic curves on the learned data-ma…

When Can Neural Networks Learn Connected Decision Regions?

2019-01-25 · Trung Le, Dinh Phung

Previous work has questioned the conditions under which the decision regions of a neural network are connected and further showed the implications of the corresponding theory to the problem of adversarial manipulation of…

Neural Networks Should Be Wide Enough to Learn Disconnected Decision Regions

2018-02-28 · ICML 2018 7 · Quynh Nguyen, Mahesh Chandra Mukkamala, Matthias Hein

In the recent literature the important role of depth in deep learning has been emphasized. In this paper we argue that sufficient width of a feedforward network is equally important by answering the simple question under…

Empirical Study of the Topology and Geometry of Deep Networks

2018-06-01 · CVPR 2018 6 · Alhussein Fawzi, Seyed-Mohsen Moosavi-Dezfooli, Pascal Frossard, Stefano Soatto

The goal of this paper is to analyze the geometric properties of deep neural network image classifiers in the input space. We specifically study the topology of classification regions created by deep networks, as well as…

General Classification

Classification regions of deep neural networks

2017-05-26 · Alhussein Fawzi, Seyed-Mohsen Moosavi-Dezfooli, Pascal Frossard, Stefano Soatto

The goal of this paper is to analyze the geometric properties of deep neural network classifiers in the input space. We specifically study the topology of classification regions created by deep networks, as well as their…

ClassificationGeneral Classification