arXiv subjects

Yuan Xie

Publications and source records attributed to Yuan Xie.

252 records · Page 14Linked to original sources

arXiv2018

Weakly Supervised Salient Object Detection Using Image Labels

Deep learning based salient object detection has recently achieved great success with its performance greatly outperforms any other unsupervised methods. However, annotating per-pixel saliency masks is a tedious and inefficient procedure. In this paper, we note that superior salient object detection can be obtained by iteratively mining and correcting the labeling ambiguity on saliency maps from traditional unsupervised methods. We propose to use the combination of a coarse salient object activation map from the classification network and saliency maps generated from unsupervised methods as pixel-level annotation, and develop a simple yet very effective algorithm to train fully convolutional networks for salient object detection supervised by these noisy annotations. Our algorithm is based on alternately exploiting a graphical model and training a fully convolutional network for model updating. The graphical model corrects the internal labeling ambiguity through spatial consistency and structure preserving while the fully convolutional network helps to correct the cross-image semantic ambiguity and simultaneously update the coarse activation map for next iteration. Experimental results demonstrate that our proposed method greatly outperforms all state-of-the-art unsupervised saliency detection methods and can be comparable to the current best strongly-supervised methods training with thousands of pixel-level saliency map annotations on all public benchmarks.

cs.CV↗

arXiv2018

L1-Norm Batch Normalization for Efficient Training of Deep Neural Networks

Batch Normalization (BN) has been proven to be quite effective at accelerating and improving the training of deep neural networks (DNNs). However, BN brings additional computation, consumes more memory and generally slows down the training process by a large margin, which aggravates the training effort. Furthermore, the nonlinear square and root operations in BN also impede the low bit-width quantization techniques, which draws much attention in deep learning hardware community. In this work, we propose an L1-norm BN (L1BN) with only linear operations in both the forward and the backward propagations during training. L1BN is shown to be approximately equivalent to the original L2-norm BN (L2BN) by multiplying a scaling factor. Experiments on various convolutional neural networks (CNNs) and generative adversarial networks (GANs) reveal that L1BN maintains almost the same accuracies and convergence rates compared to L2BN but with higher computational efficiency. On FPGA platform, the proposed signum and absolute operations in L1BN can achieve 1.5$\times$ speedup and save 50\% power consumption, compared with the original costly square and root operations, respectively. This hardware-friendly normalization method not only surpasses L2BN in speed, but also simplify the hardware design of ASIC accelerators with higher energy efficiency. Last but not the least, L1BN promises a fully quantized training of DNNs, which is crucial to future adaptive terminal devices.

cs.LG↗

arXiv2018

PIRT: A Runtime Framework to Enable Energy-Efficient Real-Time Robotic Applications on Heterogeneous Architectures

Enabling full robotic workloads with diverse behaviors on mobile systems with stringent resource and energy constraints remains a challenge. In recent years, attempts have been made to deploy single-accelerator-based computing platforms (such as GPU, DSP, or FPGA) to address this challenge, but with little success. The core problem is two-fold: firstly, different robotic tasks require different accelerators, and secondly, managing multiple accelerators simultaneously is overwhelming for developers. In this paper, we propose PIRT, the first robotic runtime framework to efficiently manage dynamic task executions on mobile systems with multiple accelerators as well as on the cloud to achieve better performance and energy savings. With PIRT, we enable a robot to simultaneously perform autonomous navigation with 25 FPS of localization, obstacle detection with 3 FPS, route planning, large map generation, and scene understanding, traveling at a max speed of 5 miles per hour, all within an 11W computing power envelope.

cs.RO↗

arXiv2018

Bridging the Gap Between Neural Networks and Neuromorphic Hardware with A Neural Network Compiler

Different from developing neural networks (NNs) for general-purpose processors, the development for NN chips usually faces with some hardware-specific restrictions, such as limited precision of network signals and parameters, constrained computation scale, and limited types of non-linear functions. This paper proposes a general methodology to address the challenges. We decouple the NN applications from the target hardware by introducing a compiler that can transform an existing trained, unrestricted NN into an equivalent network that meets the given hardware's constraints. We propose multiple techniques to make the transformation adaptable to different kinds of NN chips, and reliable for restrict hardware constraints. We have built such a software tool that supports both spiking neural networks (SNNs) and traditional artificial neural networks (ANNs). We have demonstrated its effectiveness with a fabricated neuromorphic chip and a processing-in-memory (PIM) design. Tests show that the inference error caused by this solution is insignificant and the transformation time is much shorter than the retraining time. Also, we have studied the parameter-sensitivity evaluations to explore the tradeoffs between network error and resource utilization for different transformation strategies, which could provide insights for co-design optimization of neuromorphic hardware and software.

cs.NE↗

arXiv2017

Effective Image Retrieval via Multilinear Multi-index Fusion

Multi-index fusion has demonstrated impressive performances in retrieval task by integrating different visual representations in a unified framework. However, previous works mainly consider propagating similarities via neighbor structure, ignoring the high order information among different visual representations. In this paper, we propose a new multi-index fusion scheme for image retrieval. By formulating this procedure as a multilinear based optimization problem, the complementary information hidden in different indexes can be explored more thoroughly. Specially, we first build our multiple indexes from various visual representations. Then a so-called index-specific functional matrix, which aims to propagate similarities, is introduced for updating the original index. The functional matrices are then optimized in a unified tensor space to achieve a refinement, such that the relevant images can be pushed more closer. The optimization problem can be efficiently solved by the augmented Lagrangian method with theoretical convergence guarantee. Unlike the traditional multi-index fusion scheme, our approach embeds the multi-index subspace structure into the new indexes with sparse constraint, thus it has little additional memory consumption in online query stage. Experimental evaluation on three benchmark datasets reveals that the proposed approach achieves the state-of-the-art performance, i.e., N-score 3.94 on UKBench, mAP 94.1\% on Holiday and 62.39\% on Market-1501.

cs.CV↗

arXiv2017

Robust Kernelized Multi-View Self-Representations for Clustering by Tensor Multi-Rank Minimization

Most recently, tensor-SVD is implemented on multi-view self-representation clustering and has achieved the promising results in many real-world applications such as face clustering, scene clustering and generic object clustering. However, tensor-SVD based multi-view self-representation clustering is proposed originally to solve the clustering problem in the multiple linear subspaces, leading to unsatisfactory results when dealing with the case of non-linear subspaces. To handle data clustering from the non-linear subspaces, a kernelization method is designed by mapping the data from the original input space to a new feature space in which the transformed data can be clustered by a multiple linear clustering method. In this paper, we make an optimization model for the kernelized multi-view self-representation clustering problem. We also develop a new efficient algorithm based on the alternation direction method and infer a closed-form solution. Since all the subproblems can be solved exactly, the proposed optimization algorithm is guaranteed to obtain the optimal solution. In particular, the original tensor-based multi-view self-representation clustering problem is a special case of our approach and can be solved by our algorithm. Experimental results on several popular real-world clustering datasets demonstrate that our approach achieves the state-of-the-art performance.

cs.CV↗

arXiv2017

Joint Hierarchical Category Structure Learning and Large-Scale Image Classification

We investigate the scalable image classification problem with a large number of categories. Hierarchical visual data structures are helpful for improving the efficiency and performance of large-scale multi-class classification. We propose a novel image classification method based on learning hierarchical inter-class structures. Specifically, we first design a fast algorithm to compute the similarity metric between categories, based on which a visual tree is constructed by hierarchical spectral clustering. Using the learned visual tree, a test sample label is efficiently predicted by searching for the best path over the entire tree. The proposed method is extensively evaluated on the ILSVRC2010 and Caltech 256 benchmark datasets. Experimental results show that our method obtains significantly better category hierarchies than other state-of-the-art visual tree-based methods and, therefore, much more accurate classification.

cs.CV↗

arXiv2017

On Unifying Multi-View Self-Representations for Clustering by Tensor Multi-Rank Minimization

In this paper, we address the multi-view subspace clustering problem. Our method utilizes the circulant algebra for tensor, which is constructed by stacking the subspace representation matrices of different views and then rotating, to capture the low rank tensor subspace so that the refinement of the view-specific subspaces can be achieved, as well as the high order correlations underlying multi-view data can be explored.} By introducing a recently proposed tensor factorization, namely tensor-Singular Value Decomposition (t-SVD) \cite{kilmer13}, we can impose a new type of low-rank tensor constraint on the rotated tensor to capture the complementary information from multiple views. Different from traditional unfolding based tensor norm, this low-rank tensor constraint has optimality properties similar to that of matrix rank derived from SVD, so the complementary information among views can be explored more efficiently and thoroughly. The established model, called t-SVD based Multi-view Subspace Clustering (t-SVD-MSC), falls into the applicable scope of augmented Lagrangian method, and its minimization problem can be efficiently solved with theoretical convergence guarantee and relatively low computational complexity. Extensive experimental testing on eight challenging image dataset shows that the proposed method has achieved highly competent objective performance compared to several state-of-the-art multi-view clustering methods.

cs.CV↗

arXiv2017

Instance-Level Salient Object Segmentation

Image saliency detection has recently witnessed rapid progress due to deep convolutional neural networks. However, none of the existing methods is able to identify object instances in the detected salient regions. In this paper, we present a salient instance segmentation method that produces a saliency mask with distinct object instance labels for an input image. Our method consists of three steps, estimating saliency map, detecting salient object contours and identifying salient object instances. For the first two steps, we propose a multiscale saliency refinement network, which generates high-quality salient region masks and salient object contours. Once integrated with multiscale combinatorial grouping and a MAP-based subset optimization framework, our method can generate very promising salient object instance segmentation results. To promote further research and evaluation of salient instance segmentation, we also construct a new database of 1000 images and their pixelwise salient instance annotations. Experimental results demonstrate that our proposed method is capable of achieving state-of-the-art performance on all public benchmarks for salient region detection as well as on our new dataset for salient instance segmentation.

cs.CV↗

arXiv2016

CNNLab: a Novel Parallel Framework for Neural Networks using GPU and FPGA-a Practical Study with Trade-off Analysis

Designing and implementing efficient, provably correct parallel neural network processing is challenging. Existing high-level parallel abstractions like MapReduce are insufficiently expressive while low-level tools like MPI and Pthreads leave ML experts repeatedly solving the same design challenges. However, the diversity and large-scale data size have posed a significant challenge to construct a flexible and high-performance implementation of deep learning neural networks. To improve the performance and maintain the scalability, we present CNNLab, a novel deep learning framework using GPU and FPGA-based accelerators. CNNLab provides a uniform programming model to users so that the hardware implementation and the scheduling are invisible to the programmers. At runtime, CNNLab leverages the trade-offs between GPU and FPGA before offloading the tasks to the accelerators. Experimental results on the state-of-the-art Nvidia K40 GPU and Altera DE5 FPGA board demonstrate that the CNNLab can provide a universal framework with efficient support for diverse applications without increasing the burden of the programmers. Moreover, we analyze the detailed quantitative performance, throughput, power, energy, and performance density for both approaches. Experimental results leverage the trade-offs between GPU and FPGA and provide useful practical experiences for the deep learning research community.

cs.LG↗

arXiv2016

DLAU: A Scalable Deep Learning Accelerator Unit on FPGA

As the emerging field of machine learning, deep learning shows excellent ability in solving complex learning problems. However, the size of the networks becomes increasingly large scale due to the demands of the practical applications, which poses significant challenge to construct a high performance implementations of deep learning neural networks. In order to improve the performance as well to maintain the low power cost, in this paper we design DLAU, which is a scalable accelerator architecture for large-scale deep learning networks using FPGA as the hardware prototype. The DLAU accelerator employs three pipelined processing units to improve the throughput and utilizes tile techniques to explore locality for deep learning applications. Experimental results on the state-of-the-art Xilinx FPGA board demonstrate that the DLAU accelerator is able to achieve up to 36.1x speedup comparing to the Intel Core2 processors, with the power consumption at 234mW.

cs.LG↗

arXiv2016

A Real-Time and Energy-Efficient Implementation of Difference-of-Gaussian with Flexible Thin-Film Transistors

With many advantageous features, softness and better biocompatibility, flexible electronic devices have developed rapidly and increasingly attracted attention. Many currently applications with flexible devices are sensors and drivers, while there is nearly no utilization aiming at complex computation since flexible devices have lower electron mobility, simple structure and large process variation. In this paper, we proposed an innovative method that enabled flexible devices to implement real-time and energy-efficient Difference-of-Gaussian, which illustrated feasibility and potentials for them to achieve complicated real-time computation in future generation products.

cs.ET↗

arXiv2015

Weighted Schatten $p$-Norm Minimization for Image Denoising with Local and Nonlocal Regularization

This paper presents a patch-wise low-rank based image denoising method with constrained variational model involving local and nonlocal regularization. On one hand, recent patch-wise methods can be represented as a low-rank matrix approximation problem whose convex relaxation usually depends on nuclear norm minimization (NNM). Here, we extend the NNM to the nonconvex schatten p-norm minimization with additional weights assigned to different singular values, which is referred to as the Weighted Schatten p-Norm Minimization (WSNM). An efficient algorithm is also proposed to solve the WSNM problem. The proposed WSNM not only gives better approximation to the original low-rank assumption, but also considers physical meanings of different data components. On the other hand, due to the naive aggregation schema which integrates all the denoised patches into a whole image, current patch-wise denoising methods always produce various degree of artifacts in denoised results. Therefore, to further reduce artifacts, a data-driven regularizer called Steering Total Variation (STV) combined with nonlocal TV is derived for a variational model, which imposes local and nonlocal consistency constraints on the patch-wise denoised image. A highly simple but efficient algorithm is proposed to solve this variational model with convergence guarantee. Both WSNM and local \& nonlocal consistent regularization are integrated into an iterative restoration framework to produce final results. Extensive experimental testing shows, both qualitatively and quantitatively, that the proposed method can effectively remove noise, as well as reduce artifacts compared with state-of-the-art methods.

cs.CV↗

arXiv2015

Weighted Schatten $p$-Norm Minimization for Image Denoising and Background Subtraction

Low rank matrix approximation (LRMA), which aims to recover the underlying low rank matrix from its degraded observation, has a wide range of applications in computer vision. The latest LRMA methods resort to using the nuclear norm minimization (NNM) as a convex relaxation of the nonconvex rank minimization. However, NNM tends to over-shrink the rank components and treats the different rank components equally, limiting its flexibility in practical applications. We propose a more flexible model, namely the Weighted Schatten $p$-Norm Minimization (WSNM), to generalize the NNM to the Schatten $p$-norm minimization with weights assigned to different singular values. The proposed WSNM not only gives better approximation to the original low-rank assumption, but also considers the importance of different rank components. We analyze the solution of WSNM and prove that, under certain weights permutation, WSNM can be equivalently transformed into independent non-convex $l_p$-norm subproblems, whose global optimum can be efficiently solved by generalized iterated shrinkage algorithm. We apply WSNM to typical low-level vision problems, e.g., image denoising and background subtraction. Extensive experimental results show, both qualitatively and quantitatively, that the proposed WSNM can more effectively remove noise, and model complex and dynamic scenes compared with state-of-the-art methods.

cs.CV↗

arXiv2015

A New Low-Rank Tensor Model for Video Completion

In this paper, we propose a new low-rank tensor model based on the circulant algebra, namely, twist tensor nuclear norm or t-TNN for short. The twist tensor denotes a 3-way tensor representation to laterally store 2D data slices in order. On one hand, t-TNN convexly relaxes the tensor multi-rank of the twist tensor in the Fourier domain, which allows an efficient computation using FFT. On the other, t-TNN is equal to the nuclear norm of block circulant matricization of the twist tensor in the original domain, which extends the traditional matrix nuclear norm in a block circulant way. We test the t-TNN model on a video completion application that aims to fill missing values and the experiment results validate its effectiveness, especially when dealing with video recorded by a non-stationary panning camera. The block circulant matricization of the twist tensor can be transformed into a circulant block representation with nuclear norm invariance. This representation, after transformation, exploits the horizontal translation relationship between the frames in a video, and endows the t-TNN model with a more powerful ability to reconstruct panning videos than the existing state-of-the-art low-rank models.

cs.CV↗

arXiv2014

Distortion-driven Turbulence Effect Removal using Variational Model

It remains a challenge to simultaneously remove geometric distortion and space-time-varying blur in frames captured through a turbulent atmospheric medium. To solve, or at least reduce these effects, we propose a new scheme to recover a latent image from observed frames by integrating a new variational model and distortion-driven spatial-temporal kernel regression. The proposed scheme first constructs a high-quality reference image from the observed frames using low-rank decomposition. Then, to generate an improved registered sequence, the reference image is iteratively optimized using a variational model containing a new spatial-temporal regularization. The proposed fast algorithm efficiently solves this model without the use of partial differential equations (PDEs). Next, to reduce blur variation, distortion-driven spatial-temporal kernel regression is carried out to fuse the registered sequence into one image by introducing the concept of the near-stationary patch. Applying a blind deconvolution algorithm to the fused image produces the final output. Extensive experimental testing shows, both qualitatively and quantitatively, that the proposed method can effectively alleviate distortion and blur and recover details of the original scene compared to state-of-the-art methods.

cs.CV↗

arXiv2007

Reliability-Centric High-Level Synthesis

Importance of addressing soft errors in both safety critical applications and commercial consumer products is increasing, mainly due to ever shrinking geometries, higher-density circuits, and employment of power-saving techniques such as voltage scaling and component shut-down. As a result, it is becoming necessary to treat reliability as a first-class citizen in system design. In particular, reliability decisions taken early in system design can have significant benefits in terms of design quality. Motivated by this observation, this paper presents a reliability-centric high-level synthesis approach that addresses the soft error problem. The proposed approach tries to maximize reliability of the design while observing the bounds on area and performance, and makes use of our reliability characterization of hardware components such as adders and multipliers. We implemented the proposed approach, performed experiments with several designs, and compared the results with those obtained by a prior proposal.

cs.AR↗

arXiv2007

Leakage-Aware Interconnect for On-Chip Network

On-chip networks have been proposed as the interconnect fabric for future systems-on-chip and multi-processors on chip. Power is one of the main constraints of these systems and interconnect consumes a significant portion of the power budget. In this paper, we propose four leakage-aware interconnect schemes. Our schemes achieve 10.13%~63.57% active leakage savings and 12.35%~95.96% standby leakage savings across schemes while the delay penalty ranges from 0% to 4.69%.

cs.AR↗