Robust Classification with Convolutional Prototype Learning
Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);University of Chinese Academy of Sciences(中国科学院大学);CAS Center for Excellence of Brain Science and Intelligence Technology(中国科学院脑科学与智能技术卓越创新中心)
Hong-Ming Yang, Xu-Yao Zhang, Fei Yin, Cheng-Lin Liu
Convolutional neural networks (CNNs) have been widely used for image classification. Despite its high accuracies, CNN has been shown to be easily fooled by some adversarial examples, indicating that CNN is not robust enough for pattern classification. In this paper, we argue that the lack of robustness for CNN is caused by the softmax layer, which is a totally discriminative model and based on the assumption of closed world (i.e., with a fixed number of categories). To improve the robustness, we propose a novel learning framework called convolutional prototype learning (CPL). The advantage of using prototypes is that it can well handle the open world recognition problem and therefore improve the robustness. Under the framework of CPL, we design multiple classification criteria to train the network. Moreover, a prototype loss (PL) is proposed as a regularization to improve the intra-class compactness of the feature representation, which can be viewed as a generative model based on the Gaussian assumption of different classes. Experiments on several datasets demonstrate that CPL can achieve comparable or even better results than traditional CNN, and from the robustness perspective, CPL shows great advantages for both the rejection and incremental category learning tasks.
Knowledge Distillation to Ensemble Global and Interpretable Prototype-Based Mammogram Classification Models
Australian Institute for Machine Learning, The University of Adelaide(阿德莱德大学澳大利亚机器学习研究所);St Vincent’s Institute of Medical Research(圣文森特医学研究所);St Vincent’s Hospital Melbourne(墨尔本圣文森特医院)
Learning Support and Trivial Prototypes for Interpretable Image Classification
Australian Institute for Machine Learning, University of Adelaide(阿德莱德大学澳大利亚机器学习研究所);Harvard University(哈佛大学);St Vincent’s Institute of Medical Research(圣文森特医学研究所);St Vincent’s Hospital Melbourne(墨尔本圣文森特医院);CVSSP, University of Surrey(萨里大学计算机视觉、语音与信号处理中心)
ProtoPointNet: Prototype-Based Interpretable Classification of 3D Dental Point Clouds with Verifiable Spatial Activations
Adelaide Dental School, Adelaide University(阿德莱德牙科学院,阿德莱德大学);Australian Institute for Machine Learning, Adelaide University(澳大利亚机器学习研究所,阿德莱德大学);School of Public Health, Adelaide University(阿德莱德大学公共卫生学院)
Project and Mix: Task-Semantic Prototypes for Few-Shot Image Classification
Department of Computer Science, Universitat Autònoma de Barcelona, Spain(巴塞罗那自治大学计算机科学系);Computer Vision Center, Barcelona, Spain(巴塞罗那计算机视觉中心);Media Integration and Communication Center, University of Florence, Italy(佛罗伦萨大学媒体整合与传播中心);Bernoulli Institute, University of Groningen, the Netherlands(格罗宁根大学伯努利学院);IDEAS Research Institute, Poland(波兰IDEAS研究所);ESAT-PSI, KU Leuven, Belgium(比利时KU莱顿大学ESAT-PSI)
Proto-FG3D: Prototype-based Interpretable Fine-Grained 3D Shape Classification
School of Information Science and Engineering(信息科学与工程学院);University of Jinan(济南大学);School of Control Science and Engineering(控制科学与工程学院);Shandong University(山东大学);Department of Computing and Decision Sciences(计算与决策科学系);Lingnan University(岭南大学);College of Computer Science(计算机科学学院);Nankai University(南开大学)
Supervised Classification Heads as Semantic Prototypes: Unlocking Vision-Language Alignment via Weight Recycling
Department of Computer Science and Artificial Intelligence, DaSCI Institute, University of Granada, Granada, Spain(计算机科学与人工智能系,DaSCI研究所,格拉纳达大学,格拉纳达,西班牙);Department of Mathematics ``Tullio Levi-Civita'', University of Padova, Padova, Italy(托里利-西维塔数学系,帕多瓦大学,帕多瓦,意大利)
Dual-channel Prototype Network for few-shot Classification of Pathological Images
College of Medicine and Biological Information Engineering, Northeastern University(东北大学医学与生物信息工程学院);School of Computer, National University of Defense Technology(国防科技大学计算机学院)
Prototype Learning for Micro-gesture Classification
Hefei University of Technology (HFUT)(合肥工业大学);Hefei Comprehensive National Science Center(合肥综合性国家科学中心);Zhejiang University(浙江大学);Anhui Zhonghuitong Technology Co., Ltd.(安徽中汇通科技有限公司)
A Comparison for Anti-noise Robustness of Deep Learning Classification Methods on a Tiny Object Image Dataset: from Convolutional Neural Network to Visual Transformer and Performer
Northeastern University(东北大学);University of Luebeck(吕贝克大学)
Deep Galaxy: Classification of Galaxies based on Deep Convolutional Neural Networks
Faculty of Computers and Information, Cairo University(开罗大学计算机与信息学院);National Research Institute of Astronomy and Geophysics(国家天文与地球物理研究所);Integrated Thebes Institutes(底比斯综合学院)
Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
Visual Geometry Group, University of Oxford(牛津大学视觉几何组)
本文讨论了使用深度卷积网络(ConvNets)学习的图像分类模型的可视化。我们考虑两种可视化技术,基于计算相对于输入图像的类分数的梯度。第一个生成图像,其最大化类得分[Erhan等人,2009],从而可视化类的概念,由ConvNet捕获。第二种技术计算特定于给定图像和类的类显著性图。我们表明,这样的地图可以用于弱监督对象分割使用分类ConvNets。最后,我们建立了基于梯度的ConvNet可视化方法与去卷积网络之间的联系[Zeiler et al.,2013年]。