In this work we evaluate the impact of digitally altered images on the performance of artificial neural networks. We explore factors that negatively affect the ability of an image classification model to produce consistent and accurate results. A model's ability to classify is negatively influenced by alterations to images as a result of digital abnormalities or changes in the physical environment. The focus of this paper is to discover and replicate scenarios that modify the appearance of an image and evaluate them on state-of-the-art machine learning models. Our contributions present various training techniques that enhance a model's ability to generalize and improve robustness against these alterations.
MindGarage, University of Kaiserslautern（凯泽斯劳滕大学MindGarage）；DFKI, Kaiserslautern（凯泽斯劳滕德国人工智能研究中心）；Insiders Technologies GmbH, Kaiserslautern（凯泽斯劳滕Insiders技术有限公司）；University of Fribourg（弗里堡大学）
We present an exhaustive investigation of recent Deep Learning architectures, algorithms, and strategies for the task of document image classification to finally reduce the error by more than half. Existing approaches, such as the DeepDocClassifier, apply standard Convolutional Network architectures with transfer learning from the object recognition domain. The contribution of the paper is threefold: First, it investigates recently introduced very deep neural network architectures (GoogLeNet, VGG, ResNet) using transfer learning (from real images). Second, it proposes transfer learning from a …
Improvement Strategies for Few-Shot Learning in OCT Image Classification of Rare Retinal Diseases
Department of Electrical Engineering, Yuan Ze University（电气工程系，元智大学）；Department of Electrical Engineering, National Taiwan Normal University（电气工程系，国立台湾师范大学）；Department of Ophthalmology, Far Eastern Memorial Hospital（眼科部，东部医疗院）
In this paper we present a novel method for robust hyperspectral image classification using context and rejection. Hyperspectral image classification is generally an ill-posed image problem where pixels may belong to unknown classes, and obtaining representative and complete training sets is costly. Furthermore, the need for high classification accuracies is frequently greater than the need to classify the entire image. We approach this problem with a robust classification method that combines classification with context with classification with rejection. A rejection field that will guide the…
Geometric transformations of the training data as well as the test data present challenges to the use of deep neural networks to vision-based learning tasks. In order to address this issue, we present a deep neural network model that exhibits the desirable property of transformation-robustness. Our model, termed RobustCaps, uses group-equivariant convolutions in an improved capsule network model. RobustCaps uses a global context-normalised procedure in its routing algorithm to learn transformation-invariant part-whole relationships within image data. This learning of such relationships allows …
National Institute of Radiological Sciences, QST（量子科学技术研究开发机构放射线医学综合研究所）；MNES corporation（MNES公司）；QST Hospital, QST（量子科学技术研究开发机构医院）
Purpose: To construct a neural network model that can learn the different diagnosing strategies of radiologists to better classify aneurysm status in magnetic resonance angiography images. Materials and methods: This retrospective study included 3423 time-of-flight brain magnetic resonance angiography image series (subjects: male 1843 [mean age, 50.2 +/- 11.7 years], female 1580 [50.8 +/- 11.3 years]) recorded from November 2017 through January 2019. The image series were read independently for aneurysm status by one of four board-certified radiologists, who were assisted by an established dee…
Fusion and Grouping Strategies in Deep Learning for Local Climate Zone Classification of Multimodal Remote Sensing Data
Graphics-Visualization-Computing Lab, International Institute of Information Technology Bangalore, Karnataka 560100, India（图形可视化计算实验室，国际信息学院班加罗尔，卡纳塔克邦560100，印度）
Published studies have suggested the bias of automated face-based gender classification algorithms across gender-race groups. Specifically, unequal accuracy rates were obtained for women and dark-skinned people. To mitigate the bias of gender classifiers, the vision community has developed several strategies. However, the efficacy of these mitigation strategies is demonstrated for a limited number of races mostly, Caucasian and African-American. Further, these strategies often offer a trade-off between bias and classification accuracy. To further advance the state-of-the-art, we leverage the p…
We present four different robust transfer learning and data augmentation strategies for robust mobile scene recognition. By training three mobile-ready (EfficientNetB0, MobileNetV2, MobileNetV3) and two large-scale baseline (VGG16, ResNet50) convolutional neural network architectures on the widely available Event8, Scene15, Stanford40, and MIT67 datasets, we show the generalization ability of our transfer learning strategies. Furthermore, we tested the robustness of our transfer learning strategies under viewpoint and lighting changes using the KTH-Idol2 database. Also, the impact of inference…
University of California, Los Angeles（加利福尼亚大学洛杉矶分校）；Peking University, Shenzhen（北京大学深圳研究生院）
We trained Binarized Neural Networks (BNNs) on the high resolution ImageNet ILSVRC-2102 dataset classification task and achieved a good performance. With a moderate size network of 13 layers, we obtained top-5 classification accuracy rate of 84.1 % on validation set through network distillation, much better than previous published results of 73.2% on XNOR network and 69.1% on binarized GoogleNET. We expect networks of better performance can be obtained by following our current strategies. We provide a detailed discussion and preliminary analysis on strategies used in the network training.
Efficient Waste Sorting for Circular Economy: A Confidence-guided comparison between One-Vs-All and One-Vs-Rest Classification Strategies with Human-in-the-Loop for Automated Waste Sorting
Institute for Software and Systems Engineering（软件与系统工程研究所）；Clausthal University of Technology（克莱斯特哈根技术大学）
Transfer Learning Strategies for Pathological Foundation Models: A Systematic Evaluation in Brain Tumor Classification
Hokkaido University（北海道大学）；Hokkaido University Hospital（北海道大学医院）；Nakamura Memorial Hospital（中村纪念医院）；Sapporo Azabu Neurosurgical Hospital（札幌麻布神经外科医院）；Sapporo Hakuyokai Hospital（札幌白洋会医院）；Institute for Chemical Reaction Design and Discovery (WPI-ICReDD)（化学反应设计与发现研究所（WPI-ICReDD））
Deep learning models with large learning capacities often overfit to medical imaging datasets. This is because training sets are often relatively small due to the significant time and financial costs incurred in medical data acquisition and labelling. Data augmentation is therefore often used to expand the availability of training data and to increase generalization. However, augmentation strategies are often chosen on an ad-hoc basis without justification. In this paper, we present an augmentation policy search method with the goal of improving model classification performance. We include in …
Training adversarially robust discriminative (i.e., softmax) classifier has been the dominant approach to robust classification. Building on recent work on adversarial training (AT)-based generative models, we investigate using AT to learn unnormalized class-conditional density models and then performing generative robust classification. Our result shows that, under the condition of similar model capacities, the generative robust classifier achieves comparable performance to a baseline softmax robust classifier when the test data is clean or when the test perturbation is of limited size, and m…
RMIT University（皇家墨尔本理工大学）；University College London（伦敦大学学院）
In this paper, we present a robust spherical harmonics approach for the classification of point cloud-based objects. Spherical harmonics have been used for classification over the years, with several frameworks existing in the literature. These approaches use variety of spherical harmonics based descriptors to classify objects. We first investigated these frameworks robustness against data augmentation, such as outliers and noise, as it has not been studied before. Then we propose a spherical convolution neural network framework for robust object classification. The proposed framework uses the…
Pontifícia Universidade Católica do Paraná（巴拉那天主教大学）；Universidade Federal do Paraná（巴拉那联邦大学）
When using vision-based approaches to classify individual parking spaces between occupied and empty, human experts often need to annotate the locations and label a training set containing images collected in the target parking lot to fine-tune the system. We propose investigating three annotation types (polygons, bounding boxes, and fixed-size squares), providing different data representations of the parking spaces. The rationale is to elucidate the best trade-off between handcraft annotation precision and model performance. We also investigate the number of annotated parking spaces necessary …
Institute of Medical Technology and Intelligent Systems, Hamburg University of Technology（汉堡工业大学医学技术与智能系统研究所）；Department of Pediatric Hematology and Oncology, University Medical Center Hamburg-Eppendorf（汉堡-埃彭多夫大学医学中心儿科血液学与肿瘤学系）；Mildred Scheel Cancer Career Center HaTriCS4, University Medical Center Hamburg-Eppendorf（汉堡-埃彭多夫大学医学中心米尔德丽德·谢尔癌症职业中心HaTriCS4）；Institute of Neuropathology, University Medical Center Hamburg-Eppendorf（汉堡-埃彭多夫大学医学中心神经病理学研究所）
Medulloblastoma (MB) is a primary central nervous system tumor and the most common malignant brain cancer among children. Neuropathologists perform microscopic inspection of histopathological tissue slides under a microscope to assess the severity of the tumor. This is a time-consuming task and often infused with observer variability. Recently, pre-trained convolutional neural networks (CNN) have shown promising results for MB subtype classification. Typically, high-resolution images are divided into smaller tiles for classification, while the size of the tiles has not been systematically eval…
This empirical study is mainly devoted to comparing four tree-based boosting algorithms: mart, abc-mart, robust logitboost, and abc-logitboost, for multi-class classification on a variety of publicly available datasets. Some of those datasets have been thoroughly tested in prior studies using a broad range of classification algorithms including SVM, neural nets, and deep learning. In terms of the empirical classification errors, our experiment results demonstrate: 1. Abc-mart considerably improves mart. 2. Abc-logitboost considerably improves (robust) logitboost. 3. Robust) logitboost} conside…
XAI-based Comparison of Input Representations for Audio Event Classification
Fraunhofer Heinrich-Hertz Institute（弗劳恩霍夫海因里希·赫兹研究所）；Technische Universität Berlin（柏林工业大学）；BIFOLD - Berlin Institute for the Foundations of Learning and Data（BIFOLD——柏林学习与数据基础研究所）
Universitat Pompeu Fabra（庞培法布拉大学）；Ecole Centrale de Nantes（南特中央理工学院）；LMU München（慕尼黑大学）；Technische Universität München（慕尼黑工业大学）；ICREA（加泰罗尼亚研究与高等教育学院）
Current deep-learning based methods do not easily integrate to clinical protocols, neither take full advantage of medical knowledge. In this work, we propose and compare several strategies relying on curriculum learning, to support the classification of proximal femur fracture from X-ray images, a challenging problem as reflected by existing intra- and inter-expert disagreement. Our strategies are derived from knowledge such as medical decision trees and inconsistencies in the annotations of multiple experts, which allows us to assign a degree of difficulty to each training sample. We demonstr…
Foundation Model-Driven Classification of Atypical Mitotic Figures with Domain-Aware Training Strategies
Wrocław University of Science and Technology（沃拉什大学科学与技术学院）；Cancer Center Sp. z o. o.（癌症中心有限公司）；Hospital for Lung Diseases - Rebirth（肺病医院-重生）；Maria Sklodowska-Curie National Research Institute of Oncology（玛丽·斯克洛多夫斯卡国家癌症研究院）；Pathology Department（病理部门）；th Military Research Hospital in Bydgoszcz（比多斯茨第10军科研医院）；Department of Tumor Pathology and Pathomorphology（肿瘤病理与组织病理学部门）；Oncology Centre Prof. Franciszek Łukaszczyk Memorial Hospital（弗雷德里克·卢卡斯茨基纪念医院肿瘤中心）；Doctoral School of Medical and Health Sciences, Nicolaus Copernicus University in Toruń（医学与健康科学博士学院，尼古拉斯·哥白尼大学图努恩分校）；Department of Obstetrics, Gynaecology and Oncology, Collegium Medicum in Bydgoszcz, Nicolaus Copernicus University in Torun（妇产科与肿瘤学系，比多斯茨医学院，尼古拉斯·哥白尼大学图努恩分校）
Agave crop segmentation and maturity classification with deep learning data-centric strategies using very high-resolution satellite imagery
Coordinación General de Innovación Gubernamental, del Gobierno de Jalisco（哈利斯科州政府政府创新总协调局）；ITESO—The Jesuit University of Guadalajara（瓜达拉哈拉伊泰索耶稣会大学）；Universidad Autónoma de Guadalajara（瓜达拉哈拉自治大学）
Birla Institute of Technology and Science Pilani（比拉理工学院）；Indian Institute of Information Technology Allahabad（印度信息技术学院阿拉哈巴德分校）
Adversarial attacks against deep learning models have gained significant attention and recent works have proposed explanations for the existence of adversarial examples and techniques to defend the models against these attacks. Attention in computer vision has been used to incorporate focused learning of important features and has led to improved accuracy. Recently, models with attention mechanisms have been proposed to enhance adversarial robustness. Following this context, this work aims at a general understanding of the impact of attention on adversarial robustness. This work presents a com…
Nanyang Technological University（南洋理工大学）；City University of Hong Kong（香港城市大学）
Deep neural networks are likely to fail when the test data is corrupted in real-world deployment (e.g., blur, weather, etc.). Test-time optimization is an effective way that adapts models to generalize to corrupted data during testing, which has been shown in the image domain. However, the techniques for improving video classification corruption robustness remain few. In this work, we propose a Temporal Coherent Test-time Optimization framework (TeCo) to utilize spatio-temporal information in test-time optimization for robust video classification. To exploit information in video with self-supe…
DeepGlint（深瞐科技）；China University of Mining and Technology（中国矿业大学）
Great progress has been made in point cloud classification with learning-based methods. However, complex scene and sensor inaccuracy in real-world application make point cloud data suffer from corruptions, such as occlusion, noise and outliers. In this work, we propose Point-Voxel based Adaptive (PV-Ada) feature abstraction for robust point cloud classification under various corruptions. Specifically, the proposed framework iteratively voxelize the point cloud and extract point-voxel feature with shared local encoding and Transformer. Then, adaptive max-pooling is proposed to robustly aggregat…
Current deep learning models for classification tasks in computer vision are trained using mini-batches. In the present article, we take advantage of the relationships between samples in a mini-batch, using graph neural networks to aggregate information from similar images. This helps mitigate the adverse effects of alterations to the input images on classification performance. Diverse experiments on image-based object and scene classification show that this approach not only improves a classifier's performance but also increases its robustness to image perturbations and adversarial attacks. F…
Quantum-Inspired Robust and Scalable SAR Object Classification
Tensor AI Solutions GmbH（Tensor AI解决方案有限公司）；Ulm University（乌尔姆大学）；Institute for Complex Quantum Systems（复杂量子系统研究所）；Hensoldt Sensors GmbH（亨索尔特传感器有限公司）；German Aerospace Center (DLR)（德国航空航天中心（DLR））；Microwaves and Radar Institute（微波与雷达研究所）
