高性能的卷积神经网络（CNN）架构必须针对特定任务进行定制，以考虑输入数据的长度、分辨率和维度。在这项工作中，我们解决了对特定问题 CNN 架构的需求。我们提出了连续卷积神经网络（CCNN）：一个单一的 CNN，能够处理任意分辨率、维度和长度的数据，而无需任何结构更改。其关键组件是其连续卷积核，在每一层对长程依赖进行建模，从而消除了当前 CNN 架构对任务相关下采样和深度的需求。我们通过在同一架构上处理序列（$1{\ m D}$）、视觉（$2{\ m D}$）和点云（$3{\ m D}$）数据任务，展示了我们方法的通用性。我们的 CCNN 在所有考虑的任务上均达到并经常超越当前最先进的水平。
英文摘要：
Performant Convolutional Neural Network (CNN) architectures must be tailored to specific tasks in order to consider the length, resolution, and dimensionality of the input data. In this work, we tackle the need for problem-specific CNN architectures. We present the Continuous Convolutional Neural Network (CCNN): a single CNN able to process data of arbitrary resolution, dimensionality and length without any structural changes. Its key component are its continuous convolutional kernels which model long-range dependencies at every layer, and thus remove the need of current CNN architectures for task-dependent downsampling and depths. We showcase the generality of our method by using the same architecture for tasks on sequential ($1{\rm D}$), visual ($2{\rm D}$) and point-cloud ($3{\rm D}$) data. Our CCNN matches and often outperforms the current state-of-the-art across all tasks considered.
This paper addresses the problem of video object segmentation, where the initial object mask is given in the first frame of an input video. We propose a novel spatio-temporal Markov Random Field (MRF) model defined over pixels to handle this problem. Unlike conventional MRF models, the spatial dependencies among pixels in our model are encoded by a Convolutional Neural Network (CNN). Specifically, for a given object, the probability of a labeling to a set of spatially neighboring pixels can be predicted by a CNN trained for this specific object. As a result, higher-order, richer dependencies a…
Existing deep convolutional neural networks (CNNs) have shown their great success on image classification. CNNs mainly consist of convolutional and pooling layers, both of which are performed on local image areas without considering the dependencies among different image regions. However, such dependencies are very important for generating explicit image representation. In contrast, recurrent neural networks (RNNs) are well known for their ability of encoding contextual information among sequential data, and they only require a limited number of network parameters. General RNNs can hardly be d…
The problem of inverse scattering proposed by Angles and Mallat in 2018, concerns training a deep neural network to invert the scattering transform applied to an image. After such a network is trained, it can be used as a generative model given that we can sample from the distribution of principal components of scattering coefficients. For this purpose, Angles and Mallat simply use samples from independent Gaussians. However, as shown in this paper, the distribution of interest can actually be very far from normal and non-negligible dependencies might exist between different coefficients. This…
Vrije Universiteit Amsterdam（阿姆斯特丹自由大学）；University of Amsterdam（阿姆斯特丹大学）；Stanford University（斯坦福大学）
The use of Convolutional Neural Networks (CNNs) is widespread in Deep Learning due to a range of desirable model properties which result in an efficient and effective machine learning framework. However, performant CNN architectures must be tailored to specific tasks in order to incorporate considerations such as the input length, resolution, and dimentionality. In this work, we overcome the need for problem-specific CNN architectures with our Continuous Convolutional Neural Network (CCNN): a single CNN architecture equipped with continuous convolutional kernels that can be used for tasks on d…
Queensland University of Technology（昆士兰科技大学）；NICTA（澳大利亚国家信息与通信技术研究院）
We propose a local modelling approach using deep convolutional neural networks (CNNs) for fine-grained image classification. Recently, deep CNNs trained from large datasets have considerably improved the performance of object recognition. However, to date there has been limited work using these deep CNNs as local feature extractors. This partly stems from CNNs having internal representations which are high dimensional, thereby making such representations difficult to model using stochastic models. To overcome this issue, we propose to reduce the dimensionality of one of the internal fully conn…
The University of Adelaide（阿德莱德大学）；Automind；Monash University（莫纳什大学）
The perceptual loss has been widely used as an effective loss term in image synthesis tasks including image super-resolution, and style transfer. It was believed that the success lies in the high-level perceptual feature representations extracted from CNNs pretrained with a large set of images. Here we reveal that, what matters is the network structure instead of the trained weights. Without any learning, the structure of a deep network is sufficient to capture the dependencies between multiple levels of variable statistics using multiple layers of CNNs. This insight removes the requirements o…
Computer Vision Center（计算机视觉中心）；Univ. Autònoma de Barcelona (UAB)（巴塞罗那自治大学）；Universitat de Barcelona（巴塞罗那大学）；Universitat Oberta de Catalunya（加泰罗尼亚开放大学）
Despite recent advances in 3D pose estimation of human hands, especially thanks to the advent of CNNs and depth cameras, this task is still far from being solved. This is mainly due to the highly non-linear dynamics of fingers, which make hand model training a challenging task. In this paper, we exploit a novel hierarchical tree-like structured CNN, in which branches are trained to become specialized in predefined subsets of hand joints, called local poses. We further fuse local pose features, extracted from hierarchical CNN branches, to learn higher order dependencies among joints in the fina…
In the domain of sequence modelling, Recurrent Neural Networks (RNN) have been capable of achieving impressive results in a variety of application areas including visual question answering, part-of-speech tagging and machine translation. However this success in modelling short term dependencies has not successfully transitioned to application areas such as trajectory prediction, which require capturing both short term and long term relationships. In this paper, we propose a Tree Memory Network (TMN) for modelling long term and short term relationships in sequence-to-sequence mapping problems. …
Military Institute of Science and Technology (MIST)（军事科学技术学院）
Vision-based deep learning models can be promising for speech-and-hearing-impaired and secret communications. While such non-verbal communications are primarily investigated with hand-gestures and facial expressions, no research endeavour is tracked so far for the lips state (i.e., open/close)-based interpretation/translation system. In support of this development, this paper reports two new Convolutional Neural Network (CNN) models for lips state detection. Building upon two prominent lips landmark detectors, DLIB and MediaPipe, we simplify lips-state model with a set of six key landmarks, an…
Monitoring the progression of lesions is important for clinical response. Summary statistics such as lesion volume are objective and easy to interpret, which can help clinicians assess lesion growth or decay. CNNs are commonly used in medical image segmentation for their ability to produce useful features within large contexts and their associated efficient iterative patch-based training. Many CNN architectures require hundreds of thousands parameters to yield a good segmentation. In this work, an efficient, computationally inexpensive CNN is implemented to estimate the number of lesion voxels…
University of Technology Sydney（悉尼科技大学）；University of Sydney（悉尼大学）；Stevens Institute of Technology（史蒂文斯理工学院）
Not all the human body parts have the same~degree of freedom~(DOF) due to the physiological structure. For example, the limbs may move more flexibly and freely than the torso does. Most of the existing 3D pose estimation methods, despite the very promising results achieved, treat the body joints equally and consequently often lead to larger reconstruction errors on the limbs. In this paper, we propose a progressive approach that explicitly accounts for the distinct DOFs among the body parts. We model parts with higher DOFs like the elbows, as dependent components of the corresponding parts wit…
Nanjing University of Science and Technology（南京理工大学）；University of Technology Sydney（悉尼科技大学）；University of Adelaide（阿德莱德大学）
Deep convolution neural networks (CNN) have demonstrated advanced performance on single-label image classification, and various progress also have been made to apply CNN methods on multi-label image classification, which requires to annotate objects, attributes, scene categories etc. in a single shot. Recent state-of-the-art approaches to multi-label image classification exploit the label dependencies in an image, at global level, largely improving the labeling capacity. However, predicting small objects and visual concepts is still challenging due to the limited discrimination of the global v…
Recently, video classification attracts intensive research efforts. However, most existing works are based on framelevel visual features, which might fail to model the temporal information, e.g. characteristics accumulated along time. In order to capture video temporal information, we propose to analyse features in frequency domain transformed by discrete Fourier transform (DFT features). Frame-level features are firstly extract by a pre-trained deep convolutional neural network (CNN). Then, time domain features are transformed and interpolated into DFT features. CNN and DFT features are furth…
Geo-ConvGRU: Geographically Masked Convolutional Gated Recurrent Unit for Bird-Eye View Segmentation
School of Instrument Science and Engineering, Harbin Institute of Technology (HIT)（哈尔滨工业大学仪器科学与工程学院）；Huawei Noah’s Ark Lab, Huawei inc.（华为诺亚方舟实验室）；School of Astronautics, Beihang University（北京航空航天大学宇航学院）
With the widespread of user-generated Internet videos, emotion recognition in those videos attracts increasing research efforts. However, most existing works are based on framelevel visual features and/or audio features, which might fail to model the temporal information, e.g. characteristics accumulated along time. In order to capture video temporal information, in this paper, we propose to analyse features in frequency domain transformed by discrete Fourier transform (DFT features). Frame-level features are firstly extract by a pre-trained deep convolutional neural network (CNN). Then, time …
Microsoft Corporation（微软公司）；Columbia University（哥伦比亚大学）
The machine learning community has recently had increased interest in the climate and disaster damage domain due to a marked increased occurrences of natural hazards (e.g., hurricanes, forest fires, floods, earthquakes). However, not enough attention has been devoted to mitigating probable destruction from impending natural hazards. We explore this crucial space by predicting building-level damages on a before-the-fact basis that would allow state actors and non-governmental organizations to be best equipped with resource distribution to minimize or preempt losses. We introduce PreDisM that em…
Hanyang University（汉阳大学）；LG AI Research（LG人工智能研究院）
Recent transformer-based super-resolution (SR) methods have achieved promising results against conventional CNN-based methods. However, these approaches suffer from essential shortsightedness created by only utilizing the standard self-attention-based reasoning. In this paper, we introduce an effective hybrid SR network to aggregate enriched features, including local features from CNNs and long-range multi-scale dependencies captured by transformers. Specifically, our network comprises transformer and convolutional branches, which synergetically complement each representation during the restor…
Recently recurrent neural networks (RNNs) have demonstrated the ability to improve scene labeling through capturing long-range dependencies among image units. In this paper, we propose dense RNNs for scene labeling by exploring various long-range semantic dependencies among image units. In comparison with existing RNN based approaches, our dense RNNs are able to capture richer contextual dependencies for each image unit via dense connections between each pair of image units, which significantly enhances their discriminative power. Besides, to select relevant and meanwhile restrain irrelevant d…
A Lightweight CNN Integrated Compact Convolutional Transformer for Multi-Scale Feature Learning and reducing computational complexity for breast cancer mammography image detection and classification
Brno University of Technology（布尔诺理工大学）；TESCAN 3DIM
In this work we present a method of automatic segmentation of defective skulls for custom cranial implant design and 3D printing purposes. Since such tissue models are usually required in patient cases with complex anatomical defects and variety of external objects present in the acquired data, most deep learning-based approaches fall short because it is not possible to create a sufficient training dataset that would encompass the spectrum of all possible structures. Because CNN segmentation experiments in this application domain have been so far limited to simple patch-based CNN architectures…
Convolutional Neural Networks (CNNs) model long-range dependencies by deeply stacking convolution operations with small window sizes, which makes the optimizations difficult. This paper presents region-based non-local (RNL) operations as a family of self-attention mechanisms, which can directly capture long-range dependencies without using a deep stack of local operations. Given an intermediate feature map, our method recalibrates the feature at a position by aggregating the information from the neighboring regions of all positions. By combining a channel attention module with the proposed RNL…
While CNN-based models have made remarkable progress on human pose estimation, what spatial dependencies they capture to localize keypoints remains unclear. In this work, we propose a model called \textbf{TransPose}, which introduces Transformer for human pose estimation. The attention layers built in Transformer enable our model to capture long-range relationships efficiently and also can reveal what dependencies the predicted keypoints rely on. To predict keypoint heatmaps, the last attention layer acts as an aggregator, which collects contributions from image clues and forms maximum positio…
Recurrent neural networks (RNNs) have shown the ability to improve scene parsing through capturing long-range dependencies among image units. In this paper, we propose dense RNNs for scene labeling by exploring various long-range semantic dependencies among image units. Different from existing RNN based approaches, our dense RNNs are able to capture richer contextual dependencies for each image unit by enabling immediate connections between each pair of image units, which significantly enhances their discriminative power. Besides, to select relevant dependencies and meanwhile to restrain irrel…
Deep convolutional neural networks (CNN) have revolutionized various fields of vision research and have seen unprecedented adoption for multiple tasks such as classification, detection, captioning, etc. However, they offer little transparency into their inner workings and are often treated as black boxes that deliver excellent performance. In this work, we aim at alleviating this opaqueness of CNNs by providing visual explanations for the network's predictions. Our approach can analyze variety of CNN based models trained for vision applications such as object recognition and caption generation…
Chowis（超维斯公司）；Gwangju Institute of Science and Technology（光州科学技术院）；Monitorapp（Monitorapp公司）
Human action recognition is one of the challenging tasks in computer vision. The current action recognition methods use computationally expensive models for learning spatio-temporal dependencies of the action. Models utilizing RGB channels and optical flow separately, models using a two-stream fusion technique, and models consisting of both convolutional neural network (CNN) and long-short term memory (LSTM) network are few examples of such complex models. Moreover, fine-tuning such complex models is computationally expensive as well. This paper proposes a deep neural network architecture for …
In this paper, we point out that the essential differences between CNN-based and Transformer-based detectors, which cause the worse performance of small objects in Transformer-based methods, are the gap between local information and global dependencies in feature extraction and propagation. To address these differences, we propose a new vision Transformer, called Hybrid Network Transformer (Hyneter), after pre-experiments that indicate the gap causes CNN-based and Transformer-based methods to increase size-different objects result unevenly. Different from the divide and conquer strategy in pre…
TractGraphFormer: Anatomically Informed Hybrid Graph CNN-Transformer Network for Interpretable Sex and Age Prediction from Diffusion MRI Tractography
Brigham and Women's Hospital, Harvard Medical School（哈佛医学院布莱根妇女医院）；University of Electronic Science and Technology of China（电子科技大学）；Beth Israel Deaconess Medical Center, Harvard Medical School（哈佛医学院贝斯以色列女执事医疗中心）；The University of Sydney（悉尼大学）；University of New South Wales（新南威尔士大学）；Boston University School of Medicine（波士顿大学医学院）；Massachusetts General Hospital, Harvard Medical School（哈佛医学院麻省总医院）
Deep neural networks have been a prevailing technique in the field of medical image processing. However, the most popular convolutional neural networks (CNNs) based methods for medical image segmentation are imperfect because they model long-range dependencies by stacking layers or enlarging filters. Transformers and the self-attention mechanism are recently proposed to effectively learn long-range dependencies by modeling all pairs of word-to-word attention regardless of their positions. The idea has also been extended to the computer vision field by creating and treating image patches as emb…
German Cancer Research Center (DKFZ)（德国癌症研究中心）；University Hospital Erlangen（埃尔兰根大学医院）；Radiological Practice at the ATOS Clinic（ATOS诊所放射科诊所）；Radiology Center Mannheim (RZM)（曼海姆放射中心）
End-to-end deep learning improves breast cancer classification on diffusion-weighted MR images (DWI) using a convolutional neural network (CNN) architecture. A limitation of CNN as opposed to previous model-based approaches is the dependence on specific DWI input channels used during training. However, in the context of large-scale application, methods agnostic towards heterogeneous inputs are desirable, due to the high deviation of scanning protocols between clinical sites. We propose model-based domain adaptation to overcome input dependencies and avoid re-training of networks at clinical si…
University of Oxford（牛津大学）；Stanford University（斯坦福大学）；Baidu Institute of Deep Learning（百度深度学习研究院）
Pixel-level labelling tasks, such as semantic segmentation, play a central role in image understanding. Recent approaches have attempted to harness the capabilities of deep learning techniques for image recognition to tackle pixel-level labelling tasks. One central issue in this methodology is the limited capacity of deep learning techniques to delineate visual objects. To solve this problem, we introduce a new form of convolutional neural network that combines the strengths of Convolutional Neural Networks (CNNs) and Conditional Random Fields (CRFs)-based probabilistic graphical modelling. To…
In image fusion, images obtained from different sensors are fused to generate a single image with enhanced information. In recent years, state-of-the-art methods have adopted Convolution Neural Networks (CNNs) to encode meaningful features for image fusion. Specifically, CNN-based methods perform image fusion by fusing local features. However, they do not consider long-range dependencies that are present in the image. Transformer-based models are designed to overcome this by modeling the long-range dependencies with the help of self-attention mechanism. This motivates us to propose a novel Ima…
Tianjin University（天津大学）；University at Albany, SUNY（纽约州立大学奥尔巴尼分校）
The structured time series (STS) classification problem requires the modeling of interweaved spatiotemporal dependency. most previous STS classification methods model the spatial and temporal dependencies independently. Due to the complexity of the STS data, we argue that a desirable STS classification method should be a holistic framework that can be made as adaptive and flexible as possible. This motivates us to design a deep neural network with such merits. Inspired by the dual-stream hypothesis in neural science, we propose a novel dual-stream framework for modeling the interweaved spatiot…
Nanyang Technological University（南洋理工大学）；Alibaba AI Labs（阿里巴巴人工智能实验室）
Language Models based on recurrent neural networks have dominated recent image caption generation tasks. In this paper, we introduce a Language CNN model which is suitable for statistical language modeling tasks and shows competitive performance in image captioning. In contrast to previous models which predict next word based on one previous word and hidden state, our language CNN is fed with all the previous words and can model the long-range dependencies of history words, which are critical for image captioning. The effectiveness of our approach is validated on two datasets MS COCO and Flick…
We present a CNN-based predictive lossless compression scheme for raw color mosaic images of digital cameras. This specialized application problem was previously understudied but it is now becoming increasingly important, because modern CNN methods for image restoration tasks (e.g., superresolution, low lighting enhancement, deblurring), must operate on original raw mosaic images to obtain the best possible results. The key innovation of this paper is a high-order nonlinear CNN predictor of spatial-spectral mosaic patterns. The deep learning prediction can model highly complex sample dependenc…
Guangdong Ocean University（广东海洋大学）；University of Aberdeen（阿伯丁大学）；Tianjin University of Technology（天津理工大学）；Guangdong University of Technology（广东工业大学）
In this paper, we propose an end-to-end CNN-LSTM model for generating descriptions for sequential images with a local-object attention mechanism. To generate coherent descriptions, we capture global semantic context using a multi-layer perceptron, which learns the dependencies between sequential images. A paralleled LSTM network is exploited for decoding the sequence descriptions. Experimental results show that our model outperforms the baseline across three different evaluation metrics on the datasets published by Microsoft.
In this paper, we propose to use deep 3-dimensional convolutional networks (3D CNNs) in order to address the challenge of modelling spectro-temporal dynamics for speech emotion recognition (SER). Compared to a hybrid of Convolutional Neural Network and Long-Short-Term-Memory (CNN-LSTM), our proposed 3D CNNs simultaneously extract short-term and long-term spectral features with a moderate number of parameters. We evaluated our proposed and other state-of-the-art methods in a speaker-independent manner using aggregated corpora that give a large and diverse set of speakers. We found that 1) shall…
While deep convolutional neural networks (CNNs) have shown a great success in single-label image classification, it is important to note that real world images generally contain multiple labels, which could correspond to different objects, scenes, actions and attributes in an image. Traditional approaches to multi-label image classification learn independent classifiers for each category and employ ranking or thresholding on the classification results. These techniques, although working well, fail to explicitly exploit the label dependencies in an image. In this paper, we utilize recurrent neu…
Convolutional neural networks (CNNs) have been demonstrated to be highly effective in the field of pulmonary nodule detection. However, existing CNN based pulmonary nodule detection methods lack the ability to capture long-range dependencies, which is vital for global information extraction. In computer vision tasks, non-local operations have been widely utilized, but the computational cost could be very high for 3D computed tomography (CT) images. To address this issue, we propose a long short slice-aware network (LSSANet) for the detection of pulmonary nodules. In particular, we develop a ne…
Recently, deep learning methods have achieved state-of-the-art performance in many medical image segmentation tasks. Many of these are based on convolutional neural networks (CNNs). For such methods, the encoder is the key part for global and local information extraction from input images; the extracted features are then passed to the decoder for predicting the segmentations. In contrast, several recent works show a superior performance with the use of transformers, which can better model long-range spatial dependencies and capture low-level details. However, transformer as sole encoder underp…
Vellore Institute of Technology（韦洛尔理工学院）；Indian Institute of Technology Madras（印度理工学院马德拉斯分校）
Neural Networks are prone to having lesser accuracy in the classification of images with noise perturbation. Convolutional Neural Networks, CNNs are known for their unparalleled accuracy in the classification of benign images. But our study shows that they are extremely vulnerable to noise addition while Feed-forward Neural Networks, FNNs show very less correspondence with noise perturbation, maintaining their accuracy almost undisturbed. FNNs are observed to be better at classifying noise-intensive, single-channeled images that are just sheer noise to human vision. In our study, we have used …
University of Toronto（多伦多大学）；University of New Brunswick（新不伦瑞克大学）
Neural Architecture Search (NAS) has been pivotal in finding optimal network configurations for Convolution Neural Networks (CNNs). While many methods explore NAS from a global search-space perspective, the employed optimization schemes typically require heavy computational resources. This work introduces a method that is efficient in computationally constrained environments by examining the micro-search space of channel size. In tackling channel-size optimization, we design an automated algorithm to extract the dependencies within different connected layers of the network. In addition, we int…
University of Cambridge（剑桥大学）；Microsoft Research（微软研究院）
We propose a new method for creating computationally efficient and compact convolutional neural networks (CNNs) using a novel sparse connection structure that resembles a tree root. This allows a significant reduction in computational cost and number of parameters compared to state-of-the-art deep CNNs, without compromising accuracy, by exploiting the sparsity of inter-layer filter dependencies. We validate our approach by using it to train more efficient variants of state-of-the-art CNN architectures, evaluated on the CIFAR10 and ILSVRC datasets. Our results show similar or higher accuracy th…
