T2FNorm: Extremely Simple Scaled Train-time Feature Normalization for OOD Detection
NepAl Applied Mathematics and Informatics Institute (NAAMII)(尼泊尔应用数学与信息学研究所(NAAMII));University College London(伦敦大学学院);West Virginia University(西弗吉尼亚大学);University of Aberdeen(阿伯丁大学)
Neural networks are notorious for being overconfident predictors, posing a significant challenge to their safe deployment in real-world applications. While feature normalization has garnered considerable attention within the deep learning literature, current train-time regularization methods for Out-of-Distribution(OOD) detection are yet to fully exploit this potential. Indeed, the naive incorporation of feature normalization within neural networks does not guarantee substantial improvement in OOD detection performance. In this work, we introduce T2FNorm, a novel approach to transforming features to hyperspherical space during training, while employing non-transformed space for OOD-scoring purposes. This method yields a surprising enhancement in OOD detection capabilities without compromising model accuracy in in-distribution(ID). Our investigation demonstrates that the proposed technique substantially diminishes the norm of the features of all samples, more so in the case of out-of-distribution samples, thereby addressing the prevalent concern of overconfidence in neural networks. The proposed method also significantly improves various post-hoc OOD detection methods.
A simple normalization technique using window statistics to improve the out-of-distribution generalization on medical images
Shanghai Jiao Tong University(上海交通大学);Fudan University(复旦大学);Obstetrics and Gynecology Hospital, Institute of Reproduction and Development(妇产科医院生殖与发育研究院);Zhejiang University City College(浙江大学城市学院);Deepwise AI Lab(深睿人工智能实验室);the Second Affiliated Hospital of Zhejiang University(浙江大学医学院附属第二医院);Peking University Third Hospital(北京大学第三医院)
Three approaches to facilitate DNN generalization to objects in out-of-distribution orientations and illuminations
Fujitsu Limited(富士通有限公司);Artificial Intelligence Laboratory, Fujitsu Limited(富士通有限公司人工智能实验室);School of Engineering and Applied Sciences, Harvard University(哈佛大学工程与应用科学学院);Department of Brain and Cognitive Sciences, Massachusetts Institute of Technology(麻省理工学院脑与认知科学系)
Zero-Shot Test-Time Canonicalization using Out-of-Distribution Scoring
Artificial Intelligence Lab, Otto-von-Guericke University Magdeburg(马格德堡大学人工智能实验室);University of Rostock(罗斯托克大学);Becker Lab, University of Marburg(马尔堡大学贝克尔实验室)
Effect of Intensity Standardization on Deep Learning for WML Segmentation in Multi-Centre FLAIR MRI
Toronto Metropolitan University(多伦多都会大学);University of Toronto(多伦多大学);St. Michael’s Hospital(圣迈克尔医院);Institute of Biomedical Engineering, Science and Technology (iBEST)(生物医学工程科学与技术研究所(iBEST))
Point2RBox: Combine Knowledge from Synthetic Visual Patterns for End-to-end Oriented Object Detection with Single Point Supervision
Shanghai AI Laboratory(上海人工智能实验室);Harbin Institute of Technology(哈尔滨工业大学);Tsinghua University(清华大学);Shanghai Jiao Tong University(上海交通大学);Southeast University(东南大学)
Analysis of Dimensional Influence of Convolutional Neural Networks for Histopathological Cancer Classification
Fr. Conceicao Rodrigues Institute of Technology, Vashi(康塞桑·罗德里格斯理工学院,瓦希)
卷积神经网络可以根据手头的任务设计不同的复杂程度。本文分析了CNN架构的维度变化对其在组织学癌症分类任务上的性能的影响。研究从基线10层CNN模型开始,具有(3 X 3)卷积滤波器。此后,基线架构在多个维度上进行缩放,包括宽度、深度、分辨率以及所有这些的组合。宽度缩放涉及每CNN层灌输更多数量的神经元,而深度缩放涉及加深分层结构。分辨率缩放是通过增加输入图像的尺寸来执行的,而复合缩放涉及宽度、深度和分辨率缩放的混合组合。结果表明,组织病理学癌症扫描本质上非常复杂,因此需要将高分辨率图像馈送到卷积、最大池化、丢弃和批量归一化层的大层次结构中,以提取所有的复杂性并执行完美的分类。由于复合缩放基线模型可确保所有三个维度(宽度、深度和分辨率)都得到缩放,因此使用复合缩放可获得最佳性能。这项研究表明,CNN模型的更好的性能是通过对基线模型进行复合缩放来实现的。