Convolutional neural network (CNN) and its variants have led to many state-of-art results in various fields. However, a clear theoretical understanding about them is still lacking. Recently, multi-layer convolutional sparse coding (ML-CSC) has been proposed and proved to equal such simply stacked networks (plain networks). Here, we think three factors in each layer of it including the initialization, the dictionary design and the number of iterations greatly affect the performance of ML-CSC. Inspired by these considerations, we propose two novel multi-layer models--residual convolutional sparse coding model (Res-CSC) and mixed-scale dense convolutional sparse coding model (MSD-CSC), which have close relationship with the residual neural network (ResNet) and mixed-scale (dilated) dense neural network (MSDNet), respectively. Mathematically, we derive the shortcut connection in ResNet as a special case of a new forward propagation rule on ML-CSC. We find a theoretical interpretation of the dilated convolution and dense connection in MSDNet by analyzing MSD-CSC, which gives a clear mathematical understanding about them. We implement the iterative soft thresholding algorithm (ISTA) and its fast version to solve Res-CSC and MSD-CSC, which can employ the unfolding operation for further improvements. At last, extensive numerical experiments and comparison with competing methods demonstrate their effectiveness using three typical datasets.
Northwestern Polytechnical University（西北工业大学）；Australian National University（澳大利亚国立大学）
This paper proposes a new residual convolutional neural network (CNN) architecture for single image depth estimation. Compared with existing deep CNN based methods, our method achieves much better results with fewer training examples and model parameters. The advantages of our method come from the usage of dilated convolution, skip connection architecture and soft-weight-sum inference. Experimental evaluation on the NYU Depth V2 dataset shows that our method outperforms other state-of-the-art methods by a margin.
Recently, the study on learned iterative shrinkage thresholding algorithm (LISTA) has attracted increasing attentions. A large number of experiments as well as some theories have proved the high efficiency of LISTA for solving sparse coding problems. However, existing LISTA methods are all serial connection. To address this issue, we propose a novel extragradient based LISTA (ELISTA), which has a residual structure and theoretical guarantees. In particular, our algorithm can also provide the interpretability for Res-Net to a certain extent. From a theoretical perspective, we prove that our met…
Nanjing University of Information Science and Technology（南京信息工程大学）
Magnetic resonance imaging (MRI) reconstruction is an active inverse problem which can be addressed by conventional compressed sensing (CS) MRI algorithms that exploit the sparse nature of MRI in an iterative optimization-based manner. However, two main drawbacks of iterative optimization-based CSMRI methods are time-consuming and are limited in model capacity. Meanwhile, one main challenge for recent deep learning-based CSMRI is the trade-off between model performance and network size. To address the above issues, we develop a new multi-scale dilated network for MRI reconstruction with high s…
Czestochowa University of Technology（琴斯托霍瓦理工大学）；Uber Technologies（优步科技公司）
This work presents a hybrid and hierarchical deep learning model for mid-term load forecasting. The model combines exponential smoothing (ETS), advanced Long Short-Term Memory (LSTM) and ensembling. ETS extracts dynamically the main components of each individual time series and enables the model to learn their representation. Multi-layer LSTM is equipped with dilated recurrent skip connections and a spatial shortcut path from lower layers to allow the model to better capture long-term seasonal relationships and ensure more efficient training. A common learning procedure for LSTM and ETS, with …
The University of Texas at Austin（德克萨斯大学奥斯汀分校）；New York University（纽约大学）
In this study, with the goal of reducing the early detection miss rate of colorectal cancer (CRC) polyps, we propose utilizing a novel hyper-sensitive vision-based tactile sensor called HySenSe and a complementary and novel machine learning (ML) architecture that explores the potentials of utilizing dilated convolutions, the beneficial features of the ResNet architecture, and the transfer learning concept applied on a small dataset with the scale of hundreds of images. The proposed tactile sensor provides high-resolution 3D textural images of CRC polyps that will be used for their accurate cla…
National University of Singapore（新加坡国立大学）；Duke-NUS, Graduate Medical School（杜克-新加坡国立大学医学院）；Singapore Eye Research Institute（新加坡眼科研究所）；Singapore National Eye Centre（新加坡全国眼科中心）；Université de la Polynésie francaise（法属波利尼西亚大学）；Moorfields Eye Hospital NHS Foundation Trust（Moorfields眼科医院NHS基金会信托）；UCL Institute of Ophthalmol（伦敦大学学院眼科研究所）
Given that the neural and connective tissues of the optic nerve head (ONH) exhibit complex morphological changes with the development and progression of glaucoma, their simultaneous isolation from optical coherence tomography (OCT) images may be of great interest for the clinical diagnosis and management of this pathology. A deep learning algorithm was designed and trained to digitally stain (i.e. highlight) 6 ONH tissue layers by capturing both the local (tissue texture) and contextual information (spatial arrangement of tissues). The overall dice coefficient (mean of all tissues) was $0.91 \…
School of Computer Electronics and Information, Guangxi University（广西大学计算机与电子信息学院）；Guangxi Key Laboratory of Multimedia Communication and Network Technology, Guangxi University（广西大学广西多媒体通信与网络技术重点实验室）；School of Electrical Engineering, Guangxi University（广西大学电气工程学院）；Guangxi Key Laboratory of Power System Optimization and Energy Technology, Guangxi University（广西大学广西电力系统优化与能源技术重点实验室）
Non Intrusive Load Monitoring (NILM) or Energy Disaggregation (ED), seeks to save energy by decomposing corresponding appliances power reading from an aggregate power reading of the whole house. It is a single channel blind source separation problem (SCBSS) and difficult prediction problem because it is unidentifiable. Recent research shows that deep learning has become a growing popularity for NILM problem. The ability of neural networks to extract load features is closely related to its depth. However, deep neural network is difficult to train because of exploding gradient, vanishing gradien…
Shanghai Jiao Tong University（上海交通大学）；Michigan State University（密歇根州立大学）
Signal models based on sparse representation have received considerable attention in recent years. Compared to synthesis dictionary learning, sparsifying transform learning involves highly efficient sparse coding and operator update steps. In this work, we propose a Multi-layer Residual Sparsifying Transform (MRST) learning model wherein the transform domain residuals are jointly sparsified over layers. In particular, the transforms for the deeper layers exploit the more intricate properties of the residual maps. We investigate the application of the learned MRST model for low-dose CT reconstr…
University of Michigan - Shanghai Jiao Tong University Joint Institute, Shanghai Jiao Tong University（上海交通大学密西根学院）；Michigan State University（密歇根州立大学）；Los Alamos National Laboratory（洛斯阿拉莫斯国家实验室）
Signal models based on sparsity, low-rank and other properties have been exploited for image reconstruction from limited and corrupted data in medical imaging and other computational imaging applications. In particular, sparsifying transform models have shown promise in various applications, and offer numerous advantages such as efficiencies in sparse coding and learning. This work investigates pre-learning a two-layer extension of the transform model for image reconstruction, wherein the transform domain or filtering residuals of the image are further sparsified in the second layer. The propo…
Friedrich Miescher Institute for Biomedical Research (FMI)（弗里德里希·米歇勒生物医学研究所（FMI））；Faculty of Sciences, University of Basel（巴塞尔大学理学院）；University of Basel（巴塞尔大学）
Instance segmentation is a key step for quantitative microscopy. While several machine learning based methods have been proposed for this problem, most of them rely on computationally complex models that are trained on surrogate tasks. Building on recent developments towards end-to-end trainable instance segmentation, we propose a minimalist recurrent network called recurrent dilated convolutional network (RDCNet), consisting of a shared stacked dilated convolution (sSDC) layer that iteratively refines its output and thereby generates interpretable intermediate predictions. It is light-weight …
We study a class of real robust phase retrieval problems under a Gaussian assumption on the coding matrix when the received signal is sparsely corrupted by noise. The goal is to establish conditions on the sparsity under which the input vector can be exactly recovered. The recovery problem is formulated as the minimization of the $\ell_1$ norm of the residual. The main contribution is a robust phase retrieval counterpart to the seminal paper by Candes and Tao on compressed sensing ($\ell_1$ regression) [Decoding by linear programming. IEEE Transactions on Information Theory, 51(12):4203-4215, …
We explore the application of end-to-end stateless temporal modeling to small-footprint keyword spotting as opposed to recurrent networks that model long-term temporal dependencies using internal states. We propose a model inspired by the recent success of dilated convolutions in sequence modeling applications, allowing to train deeper architectures in resource-constrained configurations. Gated activations and residual connections are also added, following a similar configuration to WaveNet. In addition, we apply a custom target labeling that back-propagates loss from specific frames of intere…
Australian National University（澳大利亚国立大学）；Data61/CSIRO（Data61/联邦科学与工业研究组织）
This paper seeks to combine dictionary learning and hierarchical image representation in a principled way. To make dictionary atoms capturing additional information from extended receptive fields and attain improved descriptive capacity, we present a two-pass multi-resolution cascade framework for dictionary learning and sparse coding. The cascade allows collaborative reconstructions at different resolutions using the same dimensional dictionary atoms. Our jointly learned dictionary comprises atoms that adapt to the information available at the coarsest layer where the support of atoms reaches…
University of Massachusetts Lowell（马萨诸塞大学洛厄尔分校）；Bedford Veterans Affairs Medical Center（贝德福德退伍军人事务医疗中心）；University of Massachusetts Medical School（马萨诸塞大学医学院）
Automated ICD coding, which assigns the International Classification of Disease codes to patient visits, has attracted much research attention since it can save time and labor for billing. The previous state-of-the-art model utilized one convolutional layer to build document representations for predicting ICD codes. However, the lengths and grammar of text fragments, which are closely related to ICD coding, vary a lot in different documents. Therefore, a flat and fixed-length convolutional architecture may not be capable of learning good document representations. In this paper, we proposed a M…
Rutgers, the State University of New Jersey（罗格斯新泽西州立大学）
Most current speech enhancement models use spectrogram features that require an expensive transformation and result in phase information loss. Previous work has overcome these issues by using convolutional networks to learn long-range temporal correlations across high-resolution waveforms. These models, however, are limited by memory-intensive dilated convolution and aliasing artifacts from upsampling. We introduce an end-to-end fully-recurrent hourglass-shaped neural network architecture with residual connections for waveform-based single-channel speech enhancement. Our model can efficiently …
The extraction and proper utilization of convolution neural network (CNN) features have a significant impact on the performance of image super-resolution (SR). Although CNN features contain both the spatial and channel information, current deep techniques on SR often suffer to maximize performance due to using either the spatial or channel information. Moreover, they integrate such information within a deep or wide network rather than exploiting all the available features, eventually resulting in high computational complexity. To address these issues, we present a binarized feature fusion (BFF…
Indiana University（印第安纳大学）；Electronics and Telecommunications Research Institute（电子与电信研究院）
Speech codecs learn compact representations of speech signals to facilitate data transmission. Many recent deep neural network (DNN) based end-to-end speech codecs achieve low bitrates and high perceptual quality at the cost of model complexity. We propose a cross-module residual learning (CMRL) pipeline as a module carrier with each module reconstructing the residual from its preceding modules. CMRL differs from other DNN-based speech codecs, in that rather than modeling speech compression problem in a single large neural network, it optimizes a series of less-complicated modules in a two-pha…
Institute for Integrated and Intelligent Systems, Griffith University, Australia（格里菲斯大学综合智能系统研究所）；School of Artificial Intelligence, Xidian University, China（西安电子科技大学人工智能学院）
Convolutional neural networks (CNNs) with residual links (ResNets) and causal dilated convolutional units have been the network of choice for deep learning approaches to speech enhancement. While residual links improve gradient flow during training, feature diminution of shallow layer outputs can occur due to repetitive summations with deeper layer outputs. One strategy to improve feature re-usage is to fuse both ResNets and densely connected CNNs (DenseNets). DenseNets, however, over-allocate parameters for feature re-usage. Motivated by this, we propose the residual-dense lattice network (RD…
Residual Cross-Attention Transformer-Based Multi-User CSI Feedback with Deep Joint Source-Channel Coding
School of Information and Electronics, Beijing Institute of Technology（信息与电子学院，北京理工大学）；State Key Laboratory of CNS/ATM and the MIIT Key Laboratory of Complex-Field Intelligent Sensing, Beijing Institute of Technology (BIT)（国家 CNS/ATM 工程重点实验室和工信部复杂场智能感知关键实验室，北京理工大学）；Guangzhou Institute of Technology, Xidian University（广州理工大学，西安电子科技大学）
Indiana University（印第安纳大学）；Electronics and Telecommunications Research Institute（电子通信研究院）
We present a scalable and efficient neural waveform coding system for speech compression. We formulate the speech coding problem as an autoencoding task, where a convolutional neural network (CNN) performs encoding and decoding as a neural waveform codec (NWC) during its feedforward routine. The proposed NWC also defines quantization and entropy coding as a trainable module, so the coding artifacts and bitrate control are handled during the optimization process. We achieve efficiency by introducing compact model components to NWC, such as gated residual networks and depthwise separable convolu…
In video compression, coding efficiency is improved by reusing pixels from previously decoded frames via motion and residual compensation. We define two levels of hierarchical redundancy in video frames: 1) first-order: redundancy in pixel space, i.e., similarities in pixel values across neighboring frames, which is effectively captured using motion and residual compensation, 2) second-order: redundancy in motion and residual maps due to smooth motion in natural videos. While most of the existing neural video coding literature addresses first-order redundancy, we tackle the problem of capturin…
Southeast University（东南大学）；Jiangsu Intever Energy Technology Co. Ltd.（江苏英泰维能源科技有限公司）
With the increased demand on economy and efficiency of measurement technology, Non-Intrusive Load Monitoring (NILM) has received more and more attention as a cost-effective way to monitor electricity and provide feedback to users. Deep neural networks has been shown a great potential in the field of load disaggregation. In this paper, firstly, a new convolutional model based on residual blocks is proposed to avoid the degradation problem which traditional networks more or less suffer from when network layers are increased in order to learn more complex features. Secondly, we propose dilated co…
Towards the Training of Deeper Predictive Coding Neural Networks
Institute of Logic and Computation, Vienna University of Technology（逻辑与计算研究所，维也纳技术大学）；University of Oxford（牛津大学）；VERSES AI Research Lab（VERSES AI研究实验室）
Recently deep neural networks have been successfully applied in channel coding to improve the decoding performance. However, the state-of-the-art neural channel decoders cannot achieve high decoding performance and low complexity simultaneously. To overcome this challenge, in this paper we propose doubly residual neural (DRN) decoder. By integrating both the residual input and residual learning to the design of neural channel decoder, DRN enables significant decoding performance improvement while maintaining low complexity. Extensive experiment results show that on different types of channel c…
Growing Data；BioMedical Informatics center, Faculty of Medicine, Chiang Mai University（清迈大学医学院生物医学信息中心）；Faculty of Medicine, Chiang Mai University（清迈大学医学院）；Faculty of Engineering, Chiang Mai University（清迈大学工程学院）；Biomedical Engineering Institute, Chiang Mai University（清迈大学生物医学工程研究所）；Maharaj Nakhon Chiang Mai hospital（玛哈拉吉那空清迈医院）；IT department of Maharaj Nakhon Chiang Mai hospital（玛哈拉吉那空清迈医院信息技术部）
Clinical coding is an administrative process that involves the translation of diagnostic data from episodes of care into a standard code format such as ICD10. It has many critical applications such as billing and aetiology research. The automation of clinical coding is very challenging due to data sparsity, low interoperability of digital health systems, complexity of real-life diagnosis coupled with the huge size of ICD10 code space. Related work suffer from low applicability due to reliance on many data sources, inefficient modelling and less generalizable solutions. We propose a novel colla…
Massachusetts General Hospital（麻省总医院）；Harvard Medical School（哈佛医学院）；Zhejiang University（浙江大学）
Positron emission tomography (PET) is widely used for clinical diagnosis. As PET suffers from low resolution and high noise, numerous efforts try to incorporate anatomical priors into PET image reconstruction, especially with the development of hybrid PET/CT and PET/MRI systems. In this work, we proposed a novel 3D structural convolutional sparse coding (CSC) concept for penalized-likelihood PET image reconstruction, named 3D PET-CSC. The proposed 3D PET-CSC takes advantage of the convolutional operation and manages to incorporate anatomical priors without the need of registration or supervise…
Communication University of China（中国传媒大学）；Microsoft Research Asia（微软亚洲研究院）
Bitrate scalability is a desirable feature for audio coding in real-time communications. Existing neural audio codecs usually enforce a specific bitrate during training, so different models need to be trained for each target bitrate, which increases the memory footprint at the sender and the receiver side and transcoding is often needed to support multiple receivers. In this paper, we introduce a cross-scale scalable vector quantization scheme (CSVQ), in which multi-scale features are encoded progressively with stepwise feature fusion and refinement. In this way, a coarse-level signal is recon…
