Deep neural networks (DNNs) have have shown state-of-the-art performance for computer vision applications like image classification, segmentation and object detection. Whereas recent advances have shown their vulnerability to manual digital perturbations in the input data, namely adversarial attacks. The accuracy of the networks is significantly affected by the data distribution of their training dataset. Distortions or perturbations on color space of input images generates out-of-distribution data, which make networks more likely to misclassify them. In this work, we propose a color-variation dataset by distorting their RGB color on a subset of the ImageNet with 27 different combinations. The aim of our work is to study the impact of color variation on the performance of DNNs. We perform experiments on several state-of-the-art DNN architectures on the proposed dataset, and the result shows a significant correlation between color variation and loss of accuracy. Furthermore, based on the ResNet50 architecture, we demonstrate some experiments of the performance of recently proposed robust training techniques and strategies, such as Augmix, revisit, and free normalizer, on our proposed dataset. Experimental results indicate that these robust training techniques can improve the robustness of deep networks to color variation.
Attention-based Stylisation for Exemplar Image Colourisation
British Broadcasting Corporation（英国广播公司）；Insight Centre for Data Analytics & Dublin City University（洞察数据分析中心与都柏林城市大学）；Queen Mary University of London（伦敦玛丽女王大学）
H&E-adversarial network: a convolutional neural network to learn stain-invariant features through Hematoxylin & Eosin regression
Institute of Information Systems, HES-SO (University of Applied Sciences and Arts Western Switzerland)（瑞士西部应用科学与艺术大学 信息系统研究所）；Department of Computer Science, University of Geneva（日内瓦大学 计算机科学系）；Department of Neurosciences, University of Padua（帕多瓦大学 神经科学系）；Inselspital, Bern Hospital（伯尔尼大学医院）；Medical Faculty, University of Geneva（日内瓦大学 医学院）
Spatial Colour Mixing Illusions as a Perception Stress Test for Vision-Language Models
National University of Science and Technology POLITEHNICA Bucharest（波兰布加勒斯特技术大学）；IDSIA, The Dalle Molle Institute for Artificial Intelligence（达摩信息技术研究所）
How Convolutional Neural Network Architecture Biases Learned Opponency and Colour Tuning
University of Southampton（南安普顿大学）；Vision Learning and Control, Electronics and Computer Science, University of Southampton（南安普顿大学视觉学习与控制、电子与计算机科学（注：机构粒度要求到大学级别，此处完整机构为University of Southampton，其余为其内部部门，按要求提取到大学级别））
