Densely Connected Convolutional Networks (DenseNets) have been shown to achieve state-of-the-art results on image classification tasks while using fewer parameters and computation than competing methods. Since each layer in this architecture has full access to the feature maps of all previous layers, the network is freed from the burden of having to relearn previously useful features, thus alleviating issues with vanishing gradients. In this work we explore the question: To what extent is it necessary to connect to all previous layers in order to reap the benefits of feature reuse? To this end, we introduce the notion of local dense connectivity and present evidence that less connectivity, allowing for increased growth rate at a fixed network capacity, can achieve a more efficient reuse of features and lead to higher accuracy in dense architectures.
Cornell University(康奈尔大学);Fudan University(复旦大学);Facebook AI Research(Facebook AI研究院)
DenseNet架构由于功能重用而具有高度的计算效率。然而,一个简单的DenseNet实现可能需要大量的GPU内存:如果管理不当,预激活批量归一化和连续卷积操作可能会产生与网络深度成二次方增长的特征图。在本技术报告中,我们介绍了在训练过程中减少DenseNets内存消耗的策略。通过策略性地使用共享内存分配,我们将存储特征图的内存成本从二次降低到线性。没有GPU内存瓶颈,现在可以训练极深的DenseNets。具有14M参数的网络可以在单个GPU上训练,高于4M。264层DenseNet(73M参数)以前无法进行训练,现在可以在一个带有8个NVIDIA Tesla M40 GPU的工作站上进行训练。在ImageNet ILSVRC分类数据集上,这个大型DenseNet获得了20.26%的最先进的单作物前1错误。
Optimizing Convolutional Neural Networks for Chronic Obstructive Pulmonary Disease Detection in Clinical Computed Tomography Imaging
Technical University of Munich(慕尼黑工业大学);Munich Institute of Biomedical Engineering(慕尼黑生物医学工程研究所);Klinikum rechts der Isar(伊萨尔河右岸医院);Institute for Advanced Study, Technical University of Munich(慕尼黑工业大学高等研究院)
Exploring the Efficacy of Partial Denoising Using Bit Plane Slicing for Enhanced Fracture Identification: A Comparative Study of Deep Learning-Based Approaches and Handcrafted Feature Extraction Techniques
Exploring convolutional neural networks with transfer learning for diagnosing Lyme disease from skin lesion images
Université Clermont Auvergne(克莱蒙奥弗涅大学);CNRS(法国国家科学研究中心);ENSMSE(圣艾蒂安国立矿业工程师学校);INRAE(法国国家农业食品与环境研究院);VetAgro Sup(法国兽医与农学高等学院);Université de Lyon(里昂大学);CHU Clermont-Ferrand(克莱蒙费朗大学医院);Inserm(法国国家健康与医学研究院);Tous Chercheurs Laboratory(全民研究者实验室);CPIE Champenoux(尚佩努环境倡议中心);University Hospital of Nancy(南锡大学医院);University Hospital of Saint Etienne(圣艾蒂安大学医院);IHU-Méditerranée Infection(地中海感染大学医院研究所);Aix Marseille Univ(艾克斯-马赛大学);IRD(法国发展研究院);AP-HM(马赛公立医院援助机构);SSA(法国军队卫生勤务局);Hôpitaux Universitaires(斯特拉斯堡大学医院);Pontchaillou University Hospital(蓬查卢大学医院);CHR Orléans(奥尔良地区中心医院);Hospital of Villeneuve-Saint-Georges(维勒讷夫圣乔治医院);Centre Hospitalier Universitaire de Rennes(雷恩大学医院)