中文
相关论文

相关论文: Dynamical Isometry and a Mean Field Theory of CNNs…

200 篇论文

When optimizing convolutional neural networks (CNN) for a specific image-based task, specialists commonly overshoot the number of convolutional layers in their designs. By implication, these CNNs are unnecessarily resource intensive to…

机器学习 · 计算机科学 2022-06-23 Mats L. Richter , Julius Schöning , Anna Wiedenroth , Ulf Krumnack

Deep neural network is difficult to train and this predicament becomes worse as the depth increases. The essence of this problem exists in the magnitude of backpropagated errors that will result in gradient vanishing or exploding…

计算机视觉与模式识别 · 计算机科学 2017-04-11 Di Xie , Jiang Xiong , Shiliang Pu

Convolutional Neural Networks (CNNs) achieve impressive performance in a wide variety of fields. Their success benefited from a massive boost when very deep CNN models were able to be reliably trained. Despite their merits, CNNs fail to…

计算机视觉与模式识别 · 计算机科学 2019-08-20 Guohao Li , Matthias Müller , Ali Thabet , Bernard Ghanem

Convolutional kernels are basic and vital components of deep Convolutional Neural Networks (CNN). In this paper, we equip convolutional kernels with shape attributes to generate the deep Irregular Convolutional Neural Networks (ICNN).…

计算机视觉与模式识别 · 计算机科学 2017-06-27 Jiabin Ma , Wei Wang , Liang Wang

We propose a generalization of convolutional neural networks (CNNs) to irregular domains, through the use of a translation operator on a graph structure. In regular settings such as images, convolutional layers are designed by translating a…

离散数学 · 计算机科学 2018-11-06 Bastien Pasdeloup , Vincent Gripon , Jean-Charles Vialatte , Dominique Pastor , Pascal Frossard

Deep Neural Networks (DNNs) have shown unparalleled achievements in numerous applications, reflecting their proficiency in managing vast data sets. Yet, their static structure limits their adaptability in ever-changing environments. This…

计算机视觉与模式识别 · 计算机科学 2023-10-03 Yunjie Zhu , Yunhao Chen

Training a deep convolutional neural network (CNN) from scratch is difficult because it requires a large amount of labeled training data and a great deal of expertise to ensure proper convergence. A promising alternative is to fine-tune a…

计算机视觉与模式识别 · 计算机科学 2017-06-05 Nima Tajbakhsh , Jae Y. Shin , Suryakanth R. Gurudu , R. Todd Hurst , Christopher B. Kendall , Michael B. Gotway , Jianming Liang

Learning acoustic models directly from the raw waveform data with minimal processing is challenging. Current waveform-based models have generally used very few (~2) convolutional layers, which might be insufficient for building high-level…

声音 · 计算机科学 2016-10-04 Wei Dai , Chia Dai , Shuhui Qu , Juncheng Li , Samarjit Das

Recent advances in hardware and big data acquisition have accelerated the development of deep learning techniques. For an extended period of time, increasing the model complexity has led to performance improvements for various tasks.…

Convolutional Neural Networks (CNNs) are the state-of-the-art algorithms for the processing of images. However the configuration and training of these networks is a complex task requiring deep domain knowledge, experience and much trial and…

计算机视觉与模式识别 · 计算机科学 2021-02-11 Yaron Strauch , Jo Grundy

Convolutional neural networks (CNNs) have shown outstanding performance on image denoising with the help of large-scale datasets. Earlier methods naively trained a single CNN with many pairs of clean-noisy images. However, the conditional…

图像与视频处理 · 电气工程与系统科学 2021-04-05 Jae Woong Soh , Nam Ik Cho

An important goal in visual recognition is to devise image representations that are invariant to particular transformations. In this paper, we address this goal with a new type of convolutional neural network (CNN) whose invariance is…

计算机视觉与模式识别 · 计算机科学 2015-01-08 Julien Mairal , Piotr Koniusz , Zaid Harchaoui , Cordelia Schmid

Convolutional neural networks (CNN's) are powerful and widely used tools. However, their interpretability is far from ideal. One such shortcoming is the difficulty of deducing a network's ability to generalize to unseen data. We use…

计算机视觉与模式识别 · 计算机科学 2019-10-21 Rickard Brüel Gabrielsson , Gunnar Carlsson

Currently, increasingly deeper neural networks have been applied to improve their accuracy. In contrast, We propose a novel wider Convolutional Neural Networks (CNN) architecture, motivated by the Multi-column Deep Neural Networks and the…

计算机视觉与模式识别 · 计算机科学 2018-10-10 Xiaobo Huang

Very deep convolutional neural networks (CNNs) yield state of the art results on a wide variety of visual recognition problems. A number of state of the the art methods for image recognition are based on networks with well over 100 layers…

计算机视觉与模式识别 · 计算机科学 2016-07-15 Joel Moniz , Christopher Pal

Following the traditional paradigm of convolutional neural networks (CNNs), modern CNNs manage to keep pace with more recent, for example transformer-based, models by not only increasing model depth and width but also the kernel size. This…

计算机视觉与模式识别 · 计算机科学 2023-06-23 Paul Gavrikov , Janis Keuper

Recent progress in deep convolutional neural networks (CNNs) have enabled a simple paradigm of architecture design: larger models typically achieve better accuracy. Due to this, in modern CNN architectures, it becomes more important to…

机器学习 · 计算机科学 2019-05-14 Jongheon Jeong , Jinwoo Shin

The deep Convolutional Neural Network (CNN) is the state-of-the-art solution for large-scale visual recognition. Following basic principles such as increasing the depth and constructing highway connections, researchers have manually…

计算机视觉与模式识别 · 计算机科学 2017-03-07 Lingxi Xie , Alan Yuille

Initialization, normalization, and skip connections are believed to be three indispensable techniques for training very deep convolutional neural networks and obtaining state-of-the-art performance. This paper shows that deep vanilla…

计算机视觉与模式识别 · 计算机科学 2020-08-18 Haozhi Qi , Chong You , Xiaolong Wang , Yi Ma , Jitendra Malik

Skip connections and normalisation layers form two standard architectural components that are ubiquitous for the training of Deep Neural Networks (DNNs), but whose precise roles are poorly understood. Recent approaches such as Deep Kernel…

机器学习 · 计算机科学 2023-02-22 Bobby He , James Martens , Guodong Zhang , Aleksandar Botev , Andrew Brock , Samuel L Smith , Yee Whye Teh
‹ 上一页 1 2 3 10 下一页 ›