LocalNorm: Robust Image Classification through Dynamically Regularized Normalization

2019-02-18 · Bojian Yin, Siebren Schaafsma, Henk Corporaal, H. Steven Scholte, Sander M. Bohte

While modern convolutional neural networks achieve outstanding accuracy on many image classification tasks, they are, compared to humans, much more sensitive to image degradation. Here, we describe a variant of Batch Normalization, LocalNorm, that regularizes the normalization layer in the spirit of Dropout while dynamically adapting to the local image intensity and contrast at test-time. We show that the resulting deep neural networks are much more resistant to noise-induced image degradation, improving accuracy by up to three times, while achieving the same or slightly better accuracy on non-degraded classical benchmarks. In computational terms, LocalNorm adds negligible training cost and little or no cost at inference time, and can be applied to already-trained networks in a straightforward manner.

📄 PDF Abstract BibTeX arXiv:1902.06550

Code (0)

등록된 구현이 없습니다.

Tasks

Classification General Classification image-classification Image Classification

Methods 이 논문이 사용한 방법론

Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Regularizing CNN Transfer Learning with Randomised Regression

2019-08-16 · CVPR 2020 6 · Yang Zhong, Atsuto Maki

This paper is about regularizing deep convolutional networks (CNNs) based on an adaptive framework for transfer learning with limited training data in the target domain. Recent advances of CNN regularization in this cont…

regression Transfer Learning

Attention Regularized Laplace Graph for Domain Adaptation

2022-10-15 · Lingkun Luo, Liming Chen, Shiqiang Hu

In leveraging manifold learning in domain adaptation (DA), graph embedding-based DA methods have shown their effectiveness in preserving data manifold through the Laplace graph. However, current graph embedding DA method…

Domain Adaptation Graph Embedding image-classification Image Classification

SDTN and TRN: Adaptive Spectral-Spatial Feature Extraction for Hyperspectral Image Classification

2025-07-13 · Fuyin Ye, Erwen Yao, Jianyong Chen, Fengmei He 외 arxiv

Hyperspectral image classification plays a pivotal role in precision agriculture, providing accurate insights into crop health monitoring, disease detection, and soil analysis. However, traditional methods struggle with …

Hyperspectral Image Classification

High Dimensional Classification via Regularized and Unregularized Empirical Risk Minimization: Precise Error and Optimal Loss

2019-05-31 · Xiaoyi Mai, Zhenyu Liao

This article provides, through theoretical analysis, an in-depth understanding of the classification performance of the empirical risk minimization framework, in both ridge-regularized and unregularized cases, when high …

Classification General Classification

Manifold regularized kernel logistic regression for web image annotation

2013-12-21 · W. Liu, H. Liu, D. Tao, Y. Wang 외

With the rapid advance of Internet technology and smart devices, users often need to manage large amounts of multimedia information using smart devices, such as personal image and video accessing and browsing. These requ…

Binary Classification regression