Though data augmentation has become a standard component of deep neural network training, the underlying mechanism behind the effectiveness of these techniques remains poorly understood. In practice, augmentation policies are often chosen using heuristics of either distribution shift or augmentation diversity. Inspired by these, we seek to quantify how data augmentation improves model generalization. To this end, we introduce interpretable and easy-to-compute measures: Affinity and Diversity. We find that augmentation performance is predicted not by either of these alone but by jointly optimizing the two.
Impact of Data Augmentation on Confidence Calibration in Melanoma Classification
Technological University Dublin（都柏林理工大学）；Research Ireland Centre for Research Training in Machine Learning（爱尔兰研究机器学习研究培训中心）；University College Dublin（都柏林大学学院）；Dublin City University（都柏林城市大学）
Can AI-predicted complexes teach machine learning to compute drug binding affinity?
Department of Biochemistry, University of Oxford, South Parks Road, Oxford, OX1 3QU, UK；Department of Chemistry, University of Oxford, Mansfield Road, Oxford, OX1 3TA, UK；Boehringer Ingelheim Pharma GmbH \& Co. KG, Birkendorfer Str. 65, 88397 Biberach an der Riß, Germany
In this work, we shed light on different data augmentation techniques commonly used in Light Detection and Ranging (LiDAR) based 3D Object Detection. For the bulk of our experiments, we utilize the well known PointPillars pipeline and the well established KITTI dataset. We investigate a variety of global and local augmentation techniques, where global augmentation techniques are applied to the entire point cloud of a scene and local augmentation techniques are only applied to points belonging to individual objects in the scene. Our findings show that both types of data augmentation can lead to…
Uncertainty Quantification and Data Efficiency in AI: An Information-Theoretic Perspective
Institute for Intelligent Networked Systems, Northeastern University London（智能网络系统研究所，诺思安普顿大学伦敦分校）；Departments of Electrical and Computer Engineering and of Computer Science at the Technion–Israel Institute of Technology（技术ion-以色列理工学院电子与计算机工程系和计算机科学系）
Data augmentation (DA) is commonly used during model training, as it significantly improves test error and model robustness. DA artificially expands the training set by applying random noise, rotations, crops, or even adversarial perturbations to the input data. Although DA is widely used, its capacity to provably improve robustness is not fully understood. In this work, we analyze the robustness that DA begets by quantifying the margin that DA enforces on empirical risk minimizers. We first focus on linear separators, and then a class of nonlinear models whose labeling is constant within smal…
DrugCLIP: Contrastive Protein-Molecule Representation Learning for Virtual Screening
Institute for AI Industry Research（人工智能产业研究院）；Tsinghua University（清华大学）；Peking University（北京大学）；Institute of Automation（自动化研究所）；Chinese Academy of Science（中国科学院）
When Does Synthetic Data Augmentation Improve Score-Based Imbalanced Classification?
Department of Electrical & Computer Engineering, Duke University（电气与计算机工程系，杜克大学）；Department of Biostatistics & Bioinformatics, Duke University（生物统计学与生物信息学系，杜克大学）；Department of Biostatistics & Bioinformatics and Department of Computer Science, Duke University（生物统计学与生物信息学系和计算机科学系，杜克大学）
Swiss Federal Institute of Technology (EPFL)（瑞士联邦理工学院（EPFL））；Moscow Institute of Physics Technology (MIPT)（莫斯科物理技术学院（MIPT））；transfer-controls.epfl.ch（transfer-controls.epfl.ch（网址，非机构））
Transfer learning has witnessed remarkable progress in recent years, for example, with the introduction of augmentation-based contrastive self-supervised learning methods. While a number of large-scale empirical studies on the transfer performance of such models have been conducted, there is not yet an agreed-upon set of control baselines, evaluation practices, and metrics to report, which often hinders a nuanced and calibrated understanding of the real efficacy of the methods. We share an evaluation standard that aims to quantify and communicate transfer learning performance in an informative…
This paper discusses a crowdsourcing based method that we designed to quantify the importance of different attributes of a dataset in determining the outcome of a classification problem. This heuristic, provided by humans acts as the initial weight seed for machine learning models and guides the model towards a better optimal during the gradient descent process. Often times when dealing with data, it is not uncommon to deal with skewed datasets, that over represent items of certain classes, while underrepresenting the rest. Skewed datasets may lead to unforeseen issues with models such as lear…
Vicinal Feature Statistics Augmentation for Federated 3D Medical Volume Segmentation
Harvard Medical School（哈佛医学院）；Harvard University（哈佛大学）；Graduate School of Engineering, Tohoku University（东北大学工学研究生院）；School of Biomedical Engineering, Anhui Medical University（安徽医科大学生物医学工程学院）；Washington University in St. Louis（圣路易斯华盛顿大学）；The Hong Kong Polytechnic University（香港理工大学）
Evaluating the Effect of Frame Rate in Sequence-Based Classification of Autism-Related Self-Stimulatory Hand Idiosyncrasies
School of Computer Science, Carnegie Mellon University（卡内基梅隆大学计算机科学学院）；Department of Information and Computer Sciences, University of Hawai‘i at Mānoa（夏威夷大学马诺亚分校信息与计算机科学系）
CISPA Helmholtz Center for Information Security（CISPA 亥姆霍兹信息安全研究中心 (CISPA Helmholtz Center for Information Security)）
Data is the key factor to drive the development of machine learning (ML) during the past decade. However, high-quality data, in particular labeled data, is often hard and expensive to collect. To leverage large-scale unlabeled data, self-supervised learning, represented by contrastive learning, is introduced. The objective of contrastive learning is to map different views derived from a training sample (e.g., through data augmentation) closer in their representation space, while different views derived from different samples more distant. In this way, a contrastive model learns to generate inf…
Korea University（高丽大学）；NAVER Corp.（NAVER公司）；KAIST（韩国科学技术院）
Many machine learning algorithms are trained and evaluated by splitting data from a single source into training and test sets. While such focus on in-distribution learning scenarios has led to interesting advancement, it has not been able to tell if models are relying on dataset biases as shortcuts for successful prediction (e.g., using snow cues for recognising snowmobiles), resulting in biased models that fail to generalise when the bias shifts to a different class. The cross-bias generalisation problem has been addressed by de-biasing training data through augmentation or re-sampling, which…
Fraunhofer Institute for Mechanics of Materials IWM（弗劳恩霍夫材料力学研究所IWM）；Mines ParisTech PSL University（巴黎高等矿业学院PSL大学）；University of Freiburg（弗赖堡大学）；Saarland University（萨尔大学）；Material Engineering Center Saarland（萨尔兰材料工程中心）；Cardiff University（卡迪夫大学）
Materials' microstructures are signatures of their alloying composition and processing history. Therefore, microstructures exist in a wide variety. As materials become increasingly complex to comply with engineering demands, advanced computer vision (CV) approaches such as deep learning (DL) inevitably gain relevance for quantifying microstrucutures' constituents from micrographs. While DL can outperform classical CV techniques for many tasks, shortcomings are poor data efficiency and generalizability across datasets. This is inherently in conflict with the expense associated with annotating m…
