Convolutional Neural Networks (CNNs) have shown impressive performance in computer vision tasks such as image classification, detection, and segmentation. Moreover, recent work in Generative Adversarial Networks (GANs) has highlighted the importance of learning by progressively increasing the difficulty of a learning task [26]. When learning a network from scratch, the information propagated within the network during the earlier stages of training can contain distortion artifacts due to noise which can be detrimental to training. In this paper, we propose an elegant curriculum based scheme that smoothes the feature embedding of a CNN using anti-aliasing or low-pass filters. We propose to augment the train-ing of CNNs by controlling the amount of high frequency information propagated within the CNNs as training progresses, by convolving the output of a CNN feature map of each layer with a Gaussian kernel. By decreasing the variance of the Gaussian kernel, we gradually increase the amount of high-frequency information available within the network for inference. As the amount of information in the feature maps increases during training, the network is able to progressively learn better representations of the data. Our proposed augmented training scheme significantly improves the performance of CNNs on various vision tasks without either adding additional trainable parameters or an auxiliary regularization objective. The generality of our method is demonstrated through empirical performance gains in CNN architectures across four different tasks: transfer learning, cross-task transfer learning, and generative models.
Artistic Neural Style Transfer Algorithms with Activation Smoothing
University of California San Diego（加州大学圣地亚哥分校）；Tulane University（杜兰大学）；California Institute of Technology（加州理工学院）；Stevens Institute of Technology（史蒂文斯理工学院）
University of Central Florida（中佛罗里达大学）；U.S. Army Research Laboratory（美国陆军研究实验室）
During the last half decade, convolutional neural networks (CNNs) have triumphed over semantic segmentation, which is one of the core tasks in many applications such as autonomous driving. However, to train CNNs requires a considerable amount of data, which is difficult to collect and laborious to annotate. Recent advances in computer graphics make it possible to train CNNs on photo-realistic synthetic imagery with computer-generated annotations. Despite this, the domain mismatch between the real images and the synthetic data cripples the models' performance. Hence, we propose a curriculum-sty…
University of California, Berkeley（加州大学伯克利分校）；IBM T. J. Watson Research Center（IBM T. J. 沃森研究中心）
Adversarial training (AT) has become a popular choice for training robust networks. However, it tends to sacrifice clean accuracy heavily in favor of robustness and suffers from a large generalization error. To address these concerns, we propose Smooth Adversarial Training (SAT), guided by our analysis on the eigenspectrum of the loss Hessian. We find that curriculum learning, a scheme that emphasizes on starting "easy" and gradually ramping up on the "difficulty" of training, smooths the adversarial loss landscape for a suitably chosen difficulty metric. We present a general formulation for c…
EURECOM（欧洲通信系统研究院）；University of Surrey（萨里大学）；Imperial College London（帝国理工学院）
Efficient millimeter wave (mmWave) beam selection in vehicle-to-infrastructure (V2I) communication is a crucial yet challenging task due to the narrow mmWave beamwidth and high user mobility. To reduce the search overhead of iterative beam discovery procedures, contextual information from light detection and ranging (LIDAR) sensors mounted on vehicles has been leveraged by data-driven methods to produce useful side information. In this paper, we propose a lightweight neural network (NN) architecture along with the corresponding LIDAR preprocessing, which significantly outperforms previous work…
Training neural networks is traditionally done by providing a sequence of random mini-batches sampled uniformly from the entire training data. In this work, we analyze the effect of curriculum learning, which involves the non-uniform sampling of mini-batches, on the training of deep networks, and specifically CNNs trained for image recognition. To employ curriculum learning, the training algorithm must resolve 2 problems: (i) sort the training examples by difficulty; (ii) compute a series of mini-batches that exhibit an increasing level of difficulty. We address challenge (i) using two methods…
Rutgers University - New Brunswick（罗格斯大学-新不伦瑞克分校）；Department of Computer Science（计算机科学系）
Applying Global Self-attention (GSA) mechanism over features has achieved remarkable success on Convolutional Neural Networks (CNNs). However, it is not clear if Graph Convolutional Networks (GCNs) can similarly benefit from such a technique. In this paper, inspired by the similarity between CNNs and GCNs, we study the impact of the Global Self-attention mechanism on GCNs. We find that consistent with the intuition, the GSA mechanism allows GCNs to capture feature-based vertex relations regardless of edge connections; As a result, the GSA mechanism can introduce extra expressive power to the G…
For any financial organization, computing accurate quarterly forecasts for various products is one of the most critical operations. As the granularity at which forecasts are needed increases, traditional statistical time series models may not scale well. We apply deep neural networks in the forecasting domain by experimenting with techniques from Natural Language Processing (Encoder-Decoder LSTMs) and Computer Vision (Dilated CNNs), as well as incorporating transfer learning. A novel contribution of this paper is the application of curriculum learning to neural network models built for time se…
Curriculum-Enhanced Residual Soft An-Isotropic Normalization for Over-smoothness in Deep GNNs
Fuzhou University（福州大学）；HKUST (Guangzhou)（香港科技大学（广州））；Shandong Provincial Key Laboratory of Computer Networks（山东省计算机网络重点实验室）；Shandong Fundamental Research Center for Computer Science（山东计算机科学基础研究中心）
University of Southern California（南加州大学）；Chang Gung Memorial Hospital（长庚纪念医院）；University of Pennsylvania Perelman School of Medicine（宾夕法尼亚大学佩雷尔曼医学院）；Chang Gung University（长庚大学）；Amsterdam UMC, Vrije Universiteit Amsterdam（阿姆斯特丹大学医学中心，阿姆斯特丹自由大学）
There is great interest in developing radiological classifiers for diagnosis, staging, and predictive modeling in progressive diseases such as Parkinson's disease (PD), a neurodegenerative disease that is difficult to detect in its early stages. Here we leverage severity-based meta-data on the stages of disease to define a curriculum for training a deep convolutional neural network (CNN). Typically, deep learning networks are trained by randomly selecting samples in each mini-batch. By contrast, curriculum learning is a training strategy that aims to boost classifier performance by starting wi…
Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；The University of Hong Kong（香港大学）；Stanford University（斯坦福大学）
Synthesizing realistic videos of humans using neural networks has been a popular alternative to the conventional graphics-based rendering pipeline due to its high efficiency. Existing works typically formulate this as an image-to-image translation problem in 2D screen space, which leads to artifacts such as over-smoothing, missing body parts, and temporal instability of fine-scale detail, such as pose-dependent wrinkles in the clothing. In this paper, we propose a novel human video synthesis method that approaches these limiting factors by explicitly disentangling the learning of time-coherent…
Emory University（埃默里大学）；Lawrence Livermore National Laboratory（劳伦斯利弗莫尔国家实验室）
Multigrid methods are one of the most efficient techniques for solving linear systems arising from Partial Differential Equations (PDEs) and graph Laplacians from machine learning applications. One of the key components of multigrid is smoothing, which aims at reducing high-frequency errors on each grid level. However, finding optimal smoothing algorithms is problem-dependent and can impose challenges for many problems. In this paper, we propose an efficient adaptive framework for learning optimized smoothers from operator stencils in the form of convolutional neural networks (CNNs). The CNNs …
Deep learning methods are used on spectroscopic data to predict drug content in tablets from near infrared (NIR) spectra. Using convolutional neural networks (CNNs), features are ex- tracted from the spectroscopic data. Extended multiplicative scatter correction (EMSC) and a novel spectral data augmentation method are benchmarked as preprocessing steps. The learned models perform better or on par with hypothetical optimal partial least squares (PLS) models for all combinations of preprocessing. Data augmentation with subsequent EMSC in combination gave the best results. The deep learning model…
In machine learning approach to image denoising a network is trained to recover a clean image from a noisy one. In this paper a novel structure is proposed based on training multiple specialized networks as opposed to existing structures that are base on a single network. The proposed model is an alternative for training a very deep network to avoid issues like vanishing or exploding gradient. By dividing a very deep network into two smaller networks the same number of learnable parameters will be available, but two smaller networks should be trained which are easier to train. Over smoothing a…
Deep Learning has revolutionized the fields of computer vision, natural language understanding, speech recognition, information retrieval and more. Many techniques have evolved over the past decade that made models lighter, faster, and robust with better generalization. However, many deep learning practitioners persist with pre-trained models and architectures trained mostly on standard datasets such as Imagenet, MS-COCO, IMDB-Wiki Dataset, and Kinetics-700 and are either hesitant or unaware of redesigning the architecture from scratch that will lead to better performance. This scenario leads …
Valence Discovery；University of Cambridge（剑桥大学）；McGill University（麦吉尔大学）；MILA
The lack of anisotropic kernels in graph neural networks (GNNs) strongly limits their expressiveness, contributing to well-known issues such as over-smoothing. To overcome this limitation, we propose the first globally consistent anisotropic kernels for GNNs, allowing for graph convolutions that are defined according to topologicaly-derived directional flows. First, by defining a vector field in the graph, we develop a method of applying directional derivatives and smoothing by projecting node-specific messages into the field. Then, we propose the use of the Laplacian eigenvectors as such vect…
