arXiv subjects

Dacheng Tao

Publications and source records attributed to Dacheng Tao.

At least 847 records · Page 47Linked to original sources

arXiv2019

Orthogonal Deep Neural Networks

In this paper, we introduce the algorithms of Orthogonal Deep Neural Networks (OrthDNNs) to connect with recent interest of spectrally regularized deep learning methods. OrthDNNs are theoretically motivated by generalization analysis of modern DNNs, with the aim to find solution properties of network weights that guarantee better generalization. To this end, we first prove that DNNs are of local isometry on data distributions of practical interest; by using a new covering of the sample space and introducing the local isometry property of DNNs into generalization analysis, we establish a new generalization error bound that is both scale- and range-sensitive to singular value spectrum of each of networks' weight matrices. We prove that the optimal bound w.r.t. the degree of isometry is attained when each weight matrix has a spectrum of equal singular values, among which orthogonal weight matrix or a non-square one with orthonormal rows or columns is the most straightforward choice, suggesting the algorithms of OrthDNNs. We present both algorithms of strict and approximate OrthDNNs, and for the later ones we propose a simple yet effective algorithm called Singular Value Bounding (SVB), which performs as well as strict OrthDNNs, but at a much lower computational cost. We also propose Bounded Batch Normalization (BBN) to make compatible use of batch normalization with OrthDNNs. We conduct extensive comparative studies by using modern architectures on benchmark image classification. Experiments show the efficacy of OrthDNNs.

cs.LG↗

arXiv2019

Positive-Unlabeled Compression on the Cloud

Many attempts have been done to extend the great success of convolutional neural networks (CNNs) achieved on high-end GPU servers to portable devices such as smart phones. Providing compression and acceleration service of deep learning models on the cloud is therefore of significance and is attractive for end users. However, existing network compression and acceleration approaches usually fine-tuning the svelte model by requesting the entire original training data (\eg ImageNet), which could be more cumbersome than the network itself and cannot be easily uploaded to the cloud. In this paper, we present a novel positive-unlabeled (PU) setting for addressing this problem. In practice, only a small portion of the original training set is required as positive examples and more useful training examples can be obtained from the massive unlabeled data on the cloud through a PU classifier with an attention based multi-scale feature extractor. We further introduce a robust knowledge distillation (RKD) scheme to deal with the class imbalance problem of these newly augmented training examples. The superiority of the proposed method is verified through experiments conducted on the benchmark models and datasets. We can use only $8\%$ of uniformly selected data from the ImageNet to obtain an efficient model with comparable performance to the baseline ResNet-34.

cs.LG↗

arXiv2019

On Dimension-free Tail Inequalities for Sums of Random Matrices and Applications

In this paper, we present a new framework to obtain tail inequalities for sums of random matrices. Compared with existing works, our tail inequalities have the following characteristics: 1) high feasibility--they can be used to study the tail behavior of various matrix functions, e.g., arbitrary matrix norms, the absolute value of the sum of the sum of the $j$ largest singular values (resp. eigenvalues) of complex matrices (resp. Hermitian matrices); and 2) independence of matrix dimension --- they do not have the matrix-dimension term as a product factor, and thus are suitable to the scenario of high-dimensional or infinite-dimensional random matrices. The price we pay to obtain these advantages is that the convergence rate of the resulting inequalities will become slow when the number of summand random matrices is large. We also develop the tail inequalities for matrix random series and matrix martingale difference sequence. We also demonstrate usefulness of our tail bounds in several fields. In compressed sensing, we employ the resulted tail inequalities to achieve a proof of the restricted isometry property when the measurement matrix is the sum of random matrices without any assumption on the distributions of matrix entries. In probability theory, we derive a new upper bound to the supreme of stochastic processes. In machine learning, we prove new expectation bounds of sums of random matrices matrix and obtain matrix approximation schemes via random sampling. In quantum information, we show a new analysis relating to the fractional cover number of quantum hypergraphs. In theoretical computer science, we obtain randomness-efficient samplers using matrix expander graphs that can be efficiently implemented in time without dependence on matrix dimensions.

cs.LG↗

arXiv2019

Region-wise Generative Adversarial ImageInpainting for Large Missing Areas

Recently deep neutral networks have achieved promising performance for filling large missing regions in image inpainting tasks. They usually adopted the standard convolutional architecture over the corrupted image, leading to meaningless contents, such as color discrepancy, blur and artifacts. Moreover, most inpainting approaches cannot well handle the large continuous missing area cases. To address these problems, we propose a generic inpainting framework capable of handling with incomplete images on both continuous and discontinuous large missing areas, in an adversarial manner. From which, region-wise convolution is deployed in both generator and discriminator to separately handle with the different regions, namely existing regions and missing ones. Moreover, a correlation loss is introduced to capture the non-local correlations between different patches, and thus guides the generator to obtain more information during inference. With the help of our proposed framework, we can restore semantically reasonable and visually realistic images. Extensive experiments on three widely-used datasets for image inpainting tasks have been conducted, and both qualitative and quantitative experimental results demonstrate that the proposed model significantly outperforms the state-of-the-art approaches, both on the large continuous and discontinuous missing areas.

cs.CV↗

arXiv2019

Quantum algorithm for finding the negative curvature direction in non-convex optimization

We present an efficient quantum algorithm aiming to find the negative curvature direction for escaping the saddle point, which is the critical subroutine for many second-order non-convex optimization algorithms. We prove that our algorithm could produce the target state corresponding to the negative curvature direction with query complexity O(polylog(d) /ε), where d is the dimension of the optimization function. The quantum negative curvature finding algorithm is exponentially faster than any known classical method which takes time at least O(d /\sqrtε). Moreover, we propose an efficient quantum algorithm to achieve the classical read-out of the target state. Our classical read-out algorithm runs exponentially faster on the degree of d than existing counterparts.

quant-ph↗

arXiv2019

Multiple Sclerosis Lesion Inpainting Using Non-Local Partial Convolutions

Multiple sclerosis (MS) is an inflammatory demyelinating disease of the central nervous system (CNS) that results in focal injury to the grey and white matter. The presence of white matter lesions biases morphometric analyses such as registration, individual longitudinal measurements and tissue segmentation for brain volume measurements. Lesion-inpainting with intensities derived from surrounding healthy tissue represents one approach to alleviate such problems. However, existing methods inpaint lesions based on texture information derived from local surrounding tissue, often leading to inconsistent inpainting and the generation of artifacts such as intensity discrepancy and blurriness. Based on these observations, we propose non-local partial convolutions (NLPC) that integrates a Unet-like network with the non-local module. The non-local module is exploited to capture long range dependencies between the lesion area and remaining normal-appearing brain regions. Then, the lesion area is filled by referring to normal-appearing regions with more similar features. This method generates inpainted regions that appear more realistic and natural. Our quantitative experimental results also demonstrate superiority of this technique of existing state-of-the-art inpainting methods.

cs.CV↗

arXiv2019

Likelihood-Free Overcomplete ICA and Applications in Causal Discovery

Causal discovery witnessed significant progress over the past decades. In particular, many recent causal discovery methods make use of independent, non-Gaussian noise to achieve identifiability of the causal models. Existence of hidden direct common causes, or confounders, generally makes causal discovery more difficult; whenever they are present, the corresponding causal discovery algorithms can be seen as extensions of overcomplete independent component analysis (OICA). However, existing OICA algorithms usually make strong parametric assumptions on the distribution of independent components, which may be violated on real data, leading to sub-optimal or even wrong solutions. In addition, existing OICA algorithms rely on the Expectation Maximization (EM) procedure that requires computationally expensive inference of the posterior distribution of independent components. To tackle these problems, we present a Likelihood-Free Overcomplete ICA algorithm (LFOICA) that estimates the mixing matrix directly by back-propagation without any explicit assumptions on the density function of independent components. Thanks to its computational efficiency, the proposed method makes a number of causal discovery procedures much more practically feasible. For illustrative purposes, we demonstrate the computational efficiency and efficacy of our method in two causal discovery tasks on both synthetic and real data.

stat.ML↗

arXiv2019

Investigation of wind pressures on tall building under interference effects using machine learning techniques

Interference effects of tall buildings have attracted numerous studies due to the boom of clusters of tall buildings in megacities. To fully understand the interference effects of buildings, it often requires a substantial amount of wind tunnel tests. Limited wind tunnel tests that only cover part of interference scenarios are unable to fully reveal the interference effects. This study used machine learning techniques to resolve the conflicting requirement between limited wind tunnel tests that produce unreliable results and a completed investigation of the interference effects that is costly and time-consuming. Four machine learning models including decision tree, random forest, XGBoost, generative adversarial networks (GANs), were trained based on 30% of a dataset to predict both mean and fluctuating pressure coefficients on the principal building. The GANs model exhibited the best performance in predicting these pressure coefficients. A number of GANs models were then trained based on different portions of the dataset ranging from 10% to 90%. It was found that the GANs model based on 30% of the dataset is capable of predicting both mean and fluctuating pressure coefficients under unseen interference conditions accurately. By using this GANs model, 70% of the wind tunnel test cases can be saved, largely alleviating the cost of this kind of wind tunnel testing study.

cs.LG↗

arXiv2019

Multimodal Unified Attention Networks for Vision-and-Language Interactions

Learning an effective attention mechanism for multimodal data is important in many vision-and-language tasks that require a synergic understanding of both the visual and textual contents. Existing state-of-the-art approaches use co-attention models to associate each visual object (e.g., image region) with each textual object (e.g., query word). Despite the success of these co-attention models, they only model inter-modal interactions while neglecting intra-modal interactions. Here we propose a general `unified attention' model that simultaneously captures the intra- and inter-modal interactions of multimodal features and outputs their corresponding attended representations. By stacking such unified attention blocks in depth, we obtain the deep Multimodal Unified Attention Network (MUAN), which can seamlessly be applied to the visual question answering (VQA) and visual grounding tasks. We evaluate our MUAN models on two VQA datasets and three visual grounding datasets, and the results show that MUAN achieves top-level performance on both tasks without bells and whistles.

cs.CV↗

arXiv2019

Recurrent Graph Syntax Encoder for Neural Machine Translation

Syntax-incorporated machine translation models have been proven successful in improving the model's reasoning and meaning preservation ability. In this paper, we propose a simple yet effective graph-structured encoder, the Recurrent Graph Syntax Encoder, dubbed \textbf{RGSE}, which enhances the ability to capture useful syntactic information. The RGSE is done over a standard encoder (recurrent or self-attention encoder), regarding recurrent network units as graph nodes and injects syntactic dependencies as edges, such that RGSE models syntactic dependencies and sequential information (\textit{i.e.}, word order) simultaneously. Our approach achieves considerable improvements over several syntax-aware NMT models in English$\Rightarrow$German and English$\Rightarrow$Czech translation tasks. And RGSE-equipped big model obtains competitive result compared with the state-of-the-art model in WMT14 En-De task. Extensive analysis further verifies that RGSE could benefit long sentence modeling, and produces better translations.

cs.CL↗

arXiv2019

Full-Stack Filters to Build Minimum Viable CNNs

Deep convolutional neural networks (CNNs) are usually over-parameterized, which cannot be easily deployed on edge devices such as mobile phones and smart cameras. Existing works used to decrease the number or size of requested convolution filters for a minimum viable CNN on edge devices. In contrast, this paper introduces filters that are full-stack and can be used to generate many more sub-filters. Weights of these sub-filters are inherited from full-stack filters with the help of different binary masks. Orthogonal constraints are applied over binary masks to decrease their correlation and promote the diversity of generated sub-filters. To preserve the same volume of output feature maps, we can naturally reduce the number of established filters by only maintaining a few full-stack filters and a set of binary masks. We also conduct theoretical analysis on the memory cost and an efficient implementation is introduced for the convolution of the proposed filters. Experiments on several benchmark datasets and CNN models demonstrate that the proposed method is able to construct minimum viable convolution networks of comparable performance.

cs.CV↗

arXiv2019

A Quantum-inspired Algorithm for General Minimum Conical Hull Problems

A wide range of fundamental machine learning tasks that are addressed by the maximum a posteriori estimation can be reduced to a general minimum conical hull problem. The best-known solution to tackle general minimum conical hull problems is the divide-and-conquer anchoring learning scheme (DCA), whose runtime complexity is polynomial in size. However, big data is pushing these polynomial algorithms to their performance limits. In this paper, we propose a sublinear classical algorithm to tackle general minimum conical hull problems when the input has stored in a sample-based low-overhead data structure. The algorithm's runtime complexity is polynomial in the rank and polylogarithmic in size. The proposed algorithm achieves the exponential speedup over DCA and, therefore, provides advantages for high dimensional problems.

cs.LG↗

arXiv2019

Slow Feature Analysis for Human Action Recognition

Slow Feature Analysis (SFA) extracts slowly varying features from a quickly varying input signal. It has been successfully applied to modeling the visual receptive fields of the cortical neurons. Sufficient experimental results in neuroscience suggest that the temporal slowness principle is a general learning principle in visual perception. In this paper, we introduce the SFA framework to the problem of human action recognition by incorporating the discriminative information with SFA learning and considering the spatial relationship of body parts. In particular, we consider four kinds of SFA learning strategies, including the original unsupervised SFA (U-SFA), the supervised SFA (S-SFA), the discriminative SFA (D-SFA), and the spatial discriminative SFA (SD-SFA), to extract slow feature functions from a large amount of training cuboids which are obtained by random sampling in motion boundaries. Afterward, to represent action sequences, the squared first order temporal derivatives are accumulated over all transformed cuboids into one feature vector, which is termed the Accumulated Squared Derivative (ASD) feature. The ASD feature encodes the statistical distribution of slow features in an action sequence. Finally, a linear support vector machine (SVM) is trained to classify actions represented by ASD features. We conduct extensive experiments, including two sets of control experiments, two sets of large scale experiments on the KTH and Weizmann databases, and two sets of experiments on the CASIA and UT-interaction databases, to demonstrate the effectiveness of SFA for human action recognition.

cs.CV↗

arXiv2019

FAMED-Net: A Fast and Accurate Multi-scale End-to-end Dehazing Network

Single image dehazing is a critical image pre-processing step for subsequent high-level computer vision tasks. However, it remains challenging due to its ill-posed nature. Existing dehazing models tend to suffer from model overcomplexity and computational inefficiency or have limited representation capacity. To tackle these challenges, here we propose a fast and accurate multi-scale end-to-end dehazing network called FAMED-Net, which comprises encoders at three scales and a fusion module to efficiently and directly learn the haze-free image. Each encoder consists of cascaded and densely connected point-wise convolutional layers and pooling layers. Since no larger convolutional kernels are used and features are reused layer-by-layer, FAMED-Net is lightweight and computationally efficient. Thorough empirical studies on public synthetic datasets (including RESIDE) and real-world hazy images demonstrate the superiority of FAMED-Net over other representative state-of-the-art models with respect to model complexity, computational efficiency, restoration accuracy, and cross-set generalization. The code will be made publicly available.

cs.CV↗

arXiv2019

The University of Sydney's Machine Translation System for WMT19

This paper describes the University of Sydney's submission of the WMT 2019 shared news translation task. We participated in the Finnish$\rightarrow$English direction and got the best BLEU(33.0) score among all the participants. Our system is based on the self-attentional Transformer networks, into which we integrated the most recent effective strategies from academic research (e.g., BPE, back translation, multi-features data selection, data augmentation, greedy model ensemble, reranking, ConMBR system combination, and post-processing). Furthermore, we propose a novel augmentation method $Cycle Translation$ and a data mixture strategy $Big$/$Small$ parallel construction to entirely exploit the synthetic corpus. Extensive experiments show that adding the above techniques can make continuous improvements of the BLEU scores, and the best result outperforms the baseline (Transformer ensemble model trained with the original parallel corpus) by approximately 5.3 BLEU score, achieving the state-of-the-art performance.

cs.CL↗

arXiv2019

Deep Modular Co-Attention Networks for Visual Question Answering

Visual Question Answering (VQA) requires a fine-grained and simultaneous understanding of both the visual content of images and the textual content of questions. Therefore, designing an effective `co-attention' model to associate key words in questions with key objects in images is central to VQA performance. So far, most successful attempts at co-attention learning have been achieved by using shallow models, and deep co-attention models show little improvement over their shallow counterparts. In this paper, we propose a deep Modular Co-Attention Network (MCAN) that consists of Modular Co-Attention (MCA) layers cascaded in depth. Each MCA layer models the self-attention of questions and images, as well as the guided-attention of images jointly using a modular composition of two basic attention units. We quantitatively and qualitatively evaluate MCAN on the benchmark VQA-v2 dataset and conduct extensive ablation studies to explore the reasons behind MCAN's effectiveness. Experimental results demonstrate that MCAN significantly outperforms the previous state-of-the-art. Our best single model delivers 70.63$\%$ overall accuracy on the test-dev set. Code is available at https://github.com/MILVLG/mcan-vqa.

cs.CV↗

arXiv2019

Soft-ranking Label Encoding for Robust Facial Age Estimation

Automatic facial age estimation can be used in a wide range of real-world applications. However, this process is challenging due to the randomness and slowness of the aging process. Accordingly, in this paper, we propose a comprehensive framework aimed at overcoming the challenges associated with facial age estimation. First, we propose a novel age encoding method, referred to as 'Soft-ranking', which encodes two important properties of facial age, i.e., the ordinal property and the correlation between adjacent ages. Therefore, Soft-ranking provides a richer supervision signal for training deep models. Moreover, we also carefully analyze existing evaluation protocols for age estimation, finding that the overlap in identity between the training and testing sets affects the relative performance of different age encoding methods. Finally, since existing face databases for age estimation are generally small, deep models tend to suffer from an overfitting problem. To address this issue, we propose a novel regularization strategy to encourage deep models to learn more robust features from facial parts for age estimation purposes. Extensive experiments indicate that the proposed techniques improve the age estimation performance; moreover, we achieve state-of-the-art performance on the three most popular age databases, $i.e.$, Morph II, CLAP2015, and CLAP2016.

cs.CV↗

arXiv2019

ActivityNet-QA: A Dataset for Understanding Complex Web Videos via Question Answering

Recent developments in modeling language and vision have been successfully applied to image question answering. It is both crucial and natural to extend this research direction to the video domain for video question answering (VideoQA). Compared to the image domain where large scale and fully annotated benchmark datasets exists, VideoQA datasets are limited to small scale and are automatically generated, etc. These limitations restrict their applicability in practice. Here we introduce ActivityNet-QA, a fully annotated and large scale VideoQA dataset. The dataset consists of 58,000 QA pairs on 5,800 complex web videos derived from the popular ActivityNet dataset. We present a statistical analysis of our ActivityNet-QA dataset and conduct extensive experiments on it by comparing existing VideoQA baselines. Moreover, we explore various video representation strategies to improve VideoQA performance, especially for long videos. The dataset is available at https://github.com/MILVLG/activitynet-qa

cs.CV↗