arXiv subjects

Xu Liu

Publications and source records attributed to Xu Liu.

At least 253 records · Page 14Linked to original sources

arXiv2020

Feature Super-Resolution Based Facial Expression Recognition for Multi-scale Low-Resolution Faces

Facial Expressions Recognition(FER) on low-resolution images is necessary for applications like group expression recognition in crowd scenarios(station, classroom etc.). Classifying a small size facial image into the right expression category is still a challenging task. The main cause of this problem is the loss of discriminative feature due to reduced resolution. Super-resolution method is often used to enhance low-resolution images, but the performance on FER task is limited when on images of very low resolution. In this work, inspired by feature super-resolution methods for object detection, we proposed a novel generative adversary network-based feature level super-resolution method for robust facial expression recognition(FSR-FER). In particular, a pre-trained FER model was employed as feature extractor, and a generator network G and a discriminator network D are trained with features extracted from images of low resolution and original high resolution. Generator network G tries to transform features of low-resolution images to more discriminative ones by making them closer to the ones of corresponding high-resolution images. For better classification performance, we also proposed an effective classification-aware loss re-weighting strategy based on the classification probability calculated by a fixed FER model to make our model focus more on samples that are easily misclassified. Experiment results on Real-World Affective Faces (RAF) Database demonstrate that our method achieves satisfying results on various down-sample factors with a single model and has better performance on low-resolution images compared with methods using image super-resolution and expression recognition separately.

cs.CV↗

arXiv2020

An entanglement-based quantum network based on symmetric dispersive optics quantum key distribution

Quantum key distribution (QKD) is a crucial technology for information security in the future. Developing simple and efficient ways to establish QKD among multiple users are important to extend the applications of QKD in communication networks. Herein, we proposed a scheme of symmetric dispersive optics QKD (DO-QKD) and demonstrated an entanglement-based quantum network based on it. In the experiment, a broadband entanglement photon pair source was shared by end users via wavelength and space division multiplexing. The wide spectrum of generated entangled photon pairs was divided into 16 combinations of frequency-conjugate channels. Photon pairs in each channel combination supported a fully-connected subnet with 8 users by a passive beam splitter. Eventually, it showed that an entanglement-based QKD network over 100 users could be supported by one entangled photon pair source in this architecture. It has great potential on applications of local quantum networks with large user number.

quant-ph↗

arXiv2019

SLOAM: Semantic Lidar Odometry and Mapping for Forest Inventory

This paper describes an end-to-end pipeline for tree diameter estimation based on semantic segmentation and lidar odometry and mapping. Accurate mapping of this type of environment is challenging since the ground and the trees are surrounded by leaves, thorns and vines, and the sensor typically experiences extreme motion. We propose a semantic feature based pose optimization that simultaneously refines the tree models while estimating the robot pose. The pipeline utilizes a custom virtual reality tool for labeling 3D scans that is used to train a semantic segmentation network. The masked point cloud is used to compute a trellis graph that identifies individual instances and extracts relevant features that are used by the SLAM module. We show that traditional lidar and image based methods fail in the forest environment on both Unmanned Aerial Vehicle (UAV) and hand-carry systems, while our method is more robust, scalable, and automatically generates tree diameter estimations.

cs.RO↗

arXiv2019

PolSF: PolSAR image dataset on San Francisco

Polarimetric SAR data has the characteristics of all-weather, all-time and so on, which is widely used in many fields. However, the data of annotation is relatively small, which is not conducive to our research. In this paper, we have collected five open polarimetric SAR images, which are images of the San Francisco area. These five images come from different satellites at different times, which has great scientific research value. We annotate the collected images at the pixel level for image classification and segmentation. For the convenience of researchers, the annotated data is open source https://github.com/liuxuvip/PolSF.

eess.IV↗

arXiv2019

Intelligent-Unrolling: Exploiting Regular Patterns in Irregular Applications

Modern optimizing compilers are able to exploit memory access or computation patterns to generate vectorization codes. However, such patterns in irregular applications are unknown until runtime due to the input dependence. Thus, either compiler's static optimization or profile-guided optimization based on specific inputs cannot predict the patterns for any common input, which leads to suboptimal code generation. To address this challenge, we develop Intelligent-Unroll, a framework to automatically optimize irregular applications with vectorization. Intelligent-Unroll allows the users to depict the computation task using \textit{code seed} with the memory access and computation patterns represented in \textit{feature table} and \textit{information-code tree}, and generates highly efficient codes. Furthermore, Intelligent-Unroll employs several novel optimization techniques to optimize reduction operations and gather/scatter instructions. We evaluate Intelligent-Unroll with sparse matrix-vector multiplication (SpMV) and graph applications. Experimental results show that Intelligent-Unroll is able to generate more efficient vectorization codes compared to the state-of-the-art implementations.

cs.DC↗

arXiv2019

Directed-Weighting Group Lasso for Eltwise Blocked CNN Pruning

Eltwise layer is a commonly used structure in the multi-branch deep learning network. In a filter-wise pruning procedure, due to the specific operation of the eltwise layer, all its previous convolutional layers should vote for which filters by index should be pruned. Since only an intersection of the voted filters is pruned, the compression rate is limited. This work proposes a method called Directed-Weighting Group Lasso (DWGL), which enforces an index-wise incremental (directed) coefficient on the filterlevel group lasso items, so that the low index filters getting high activation tend to be kept while the high index ones tend to be pruned. When using DWGL, much fewer filters are retained during the voting process and the compression rate can be boosted. The paper test the proposed method on the ResNet series networks. On CIFAR-10, it achieved a 75.34% compression rate on ResNet-56 with a 0.94% error increment, and a 52.06% compression rate on ResNet-20 with a 0.72% error increment. On ImageNet, it achieved a 53% compression rate with ResNet-50 with a 0.6% error increment, speeding up the network by 2.23 times. Furthermore, it achieved a 75% compression rate on ResNet-50 with a 1.2% error increment, speeding up the network by 4 times.

cs.CV↗

arXiv2019

Pinpointing Performance Inefficiencies in Java

Many performance inefficiencies such as inappropriate choice of algorithms or data structures, developers' inattention to performance, and missed compiler optimizations show up as wasteful memory operations. Wasteful memory operations are those that produce/consume data to/from memory that may have been avoided. We present, JXPerf, a lightweight performance analysis tool for pinpointing wasteful memory operations in Java programs. Traditional byte-code instrumentation for such analysis (1) introduces prohibitive overheads and (2) misses inefficiencies in machine code generation. JXPerf overcomes both of these problems. JXPerf uses hardware performance monitoring units to sample memory locations accessed by a program and uses hardware debug registers to monitor subsequent accesses to the same memory. The result is a lightweight measurement at machine-code level with attribution of inefficiencies to their provenance: machine and source code within full calling contexts. JXPerf introduces only 7% runtime overhead and 7% memory overhead making it useful in production. Guided by JXPerf, we optimize several Java applications by improving code generation and choosing superior data structures and algorithms, which yield significant speedups.

cs.PF↗

arXiv2019

Wide-field 3D nanoscopy on chip through large and tunable spatial-frequency-shift effect

Linear super-resolution microscopy via synthesis aperture approach permits fast acquisition because of its wide-field implementations, however, it has been limited in resolution because a missing spatial-frequency band occurs when trying to use a shift magnitude surpassing the cutoff frequency of the detection system beyond a factor of two, which causes ghosting to appear. Here, we propose a method of chip-based 3D nanoscopy through large and tunable spatial-frequency-shift effect, capable of covering full extent of the spatial-frequency component within a wide passband. The missing of spatial-frequency can be effectively solved by developing a spatial-frequency-shift actively tuning approach through wave vector manipulation and operation of optical modes propagating along multiple azimuthal directions on a waveguide chip to interfere. In addition, the method includes a chip-based sectioning capability, which is enabled by saturated absorption of fluorophores. By introducing ultra-large propagation effective refractive index, nanoscale resolution is possible, without sacrificing the temporal resolution and the field-of-view. Imaging on GaP waveguide material demonstrates a lateral resolution of lamda/10, which is 5.4 folds above Abbe diffraction limit, and an axial resolution of lamda/19 using 0.9 NA detection objective. Simulation with an assumed propagation effective refractive index of 10 demonstrates a lateral resolution of lamda/22, in which the huge gap between the directly shifted and the zero-order components is completely filled to ensure the deep-subwavelength resolvability. It means that, a fast wide-field 3D deep-subdiffraction visualization could be realized using a standard microscope by adding a mass-producible and cost-effective spatial-frequency-shift illumination chip.

physics.optics↗

arXiv2019

PolSAR Image Classification based on Polarimetric Scattering Coding and Sparse Support Matrix Machine

POLSAR image has an advantage over optical image because it can be acquired independently of cloud cover and solar illumination. PolSAR image classification is a hot and valuable topic for the interpretation of POLSAR image. In this paper, a novel POLSAR image classification method is proposed based on polarimetric scattering coding and sparse support matrix machine. First, we transform the original POLSAR data to get a real value matrix by the polarimetric scattering coding, which is called polarimetric scattering matrix and is a sparse matrix. Second, the sparse support matrix machine is used to classify the sparse polarimetric scattering matrix and get the classification map. The combination of these two steps takes full account of the characteristics of POLSAR. The experimental results show that the proposed method can get better results and is an effective classification method.

cs.CV↗

arXiv2019

Semi-supervised Complex-valued GAN for Polarimetric SAR Image Classification

Polarimetric synthetic aperture radar (PolSAR) images are widely used in disaster detection and military reconnaissance and so on. However, their interpretation faces some challenges, e.g., deficiency of labeled data, inadequate utilization of data information and so on. In this paper, a complex-valued generative adversarial network (GAN) is proposed for the first time to address these issues. The complex number form of model complies with the physical mechanism of PolSAR data and in favor of utilizing and retaining amplitude and phase information of PolSAR data. GAN architecture and semi-supervised learning are combined to handle deficiency of labeled data. GAN expands training data and semi-supervised learning is used to train network with generated, labeled and unlabeled data. Experimental results on two benchmark data sets show that our model outperforms existing state-of-the-art models, especially for conditions with fewer labeled data.

eess.IV↗

arXiv2019

Multi-bit quantum digital signature based on quantum temporal ghost imaging

Digital signature scheme is commonly employed in modern electronic commerce and quantum digital signature (QDS) offers the information-theoretical security by the laws of quantum mechanics against attackers with unreasonable computation resources. The focus of previous QDS was on the signature of 1-bit message. In contrast, based on quantum ghost imaging with security test, we propose a scheme of QDS in which a multi-bit message can be signed at a time. Our protocol is no more demanding than the traditional cases for the requirements of quantum resources and classical communications. The multi-bit protocol could simplify the procedure of QDS for long messages in practical applications.

quant-ph↗

arXiv2019

Polarimetric Convolutional Network for PolSAR Image Classification

The approaches for analyzing the polarimetric scattering matrix of polarimetric synthetic aperture radar (PolSAR) data have always been the focus of PolSAR image classification. Generally, the polarization coherent matrix and the covariance matrix obtained by the polarimetric scattering matrix only show a limited number of polarimetric information. In order to solve this problem, we propose a sparse scattering coding way to deal with polarimetric scattering matrix and obtain a close complete feature. This encoding mode can also maintain polarimetric information of scattering matrix completely. At the same time, in view of this encoding way, we design a corresponding classification algorithm based on convolution network to combine this feature. Based on sparse scattering coding and convolution neural network, the polarimetric convolutional network is proposed to classify PolSAR images by making full use of polarimetric information. We perform the experiments on the PolSAR images acquired by AIRSAR and RADARSAT-2 to verify the proposed method. The experimental results demonstrate that the proposed method get better results and has huge potential for PolSAR data classification. Source code for sparse scattering coding is available at https://github.com/liuxuvip/Polarimetric-Scattering-Coding.

cs.CV↗

arXiv2019

Monocular Camera Based Fruit Counting and Mapping with Semantic Data Association

We present a cheap, lightweight, and fast fruit counting pipeline that uses a single monocular camera. Our pipeline that relies only on a monocular camera, achieves counting performance comparable to state-of-the-art fruit counting system that utilizes an expensive sensor suite including LiDAR and GPS/INS on a mango dataset. Our monocular camera pipeline begins with a fruit detection component that uses a deep neural network. It then uses semantic structure from motion (SFM) to convert these detections into fruit counts by estimating landmark locations of the fruit in 3D, and using these landmarks to identify double counting scenarios. There are many benefits of developing a low cost and lightweight fruit counting system, including applicability to agriculture in developing countries, where monetary constraints or unstructured environments necessitate cheaper hardware solutions.

cs.RO↗

arXiv2019

An End-to-End Network for Panoptic Segmentation

Panoptic segmentation, which needs to assign a category label to each pixel and segment each object instance simultaneously, is a challenging topic. Traditionally, the existing approaches utilize two independent models without sharing features, which makes the pipeline inefficient to implement. In addition, a heuristic method is usually employed to merge the results. However, the overlapping relationship between object instances is difficult to determine without sufficient context information during the merging process. To address the problems, we propose a novel end-to-end network for panoptic segmentation, which can efficiently and effectively predict both the instance and stuff segmentation in a single network. Moreover, we introduce a novel spatial ranking module to deal with the occlusion problem between the predicted instances. Extensive experiments have been done to validate the performance of our proposed method and promising results have been achieved on the COCO Panoptic benchmark.

cs.CV↗

arXiv2019

Evaluating Modern GPU Interconnect: PCIe, NVLink, NV-SLI, NVSwitch and GPUDirect

High performance multi-GPU computing becomes an inevitable trend due to the ever-increasing demand on computation capability in emerging domains such as deep learning, big data and planet-scale simulations. However, the lack of deep understanding on how modern GPUs can be connected and the real impact of state-of-the-art interconnect technology on multi-GPU application performance become a hurdle. In this paper, we fill the gap by conducting a thorough evaluation on five latest types of modern GPU interconnects: PCIe, NVLink-V1, NVLink-V2, NVLink-SLI and NVSwitch, from six high-end servers and HPC platforms: NVIDIA P100-DGX-1, V100-DGX-1, DGX-2, OLCF's SummitDev and Summit supercomputers, as well as an SLI-linked system with two NVIDIA Turing RTX-2080 GPUs. Based on the empirical evaluation, we have observed four new types of GPU communication network NUMA effects: three are triggered by NVLink's topology, connectivity and routing, while one is caused by PCIe chipset design issue. These observations indicate that, for an application running in a multi-GPU node, choosing the right GPU combination can impose considerable impact on GPU communication efficiency, as well as the application's overall performance. Our evaluation can be leveraged in building practical multi-GPU performance models, which are vital for GPU task allocation, scheduling and migration in a shared environment (e.g., AI cloud and HPC centers), as well as communication-oriented performance tuning.

cs.AR↗

arXiv2019

Allocating Limited Resources to Protect a Massive Number of Targets using a Game Theoretic Model

Resource allocation is the process of optimizing the rare resources. In the area of security, how to allocate limited resources to protect a massive number of targets is especially challenging. This paper addresses this resource allocation issue by constructing a game theoretic model. A defender and an attacker are players and the interaction is formulated as a trade-off between protecting targets and consuming resources. The action cost which is a necessary role of consuming resource, is considered in the proposed model. Additionally, a bounded rational behavior model (Quantal Response, QR), which simulates a human attacker of the adversarial nature, is introduced to improve the proposed model. To validate the proposed model, we compare the different utility functions and resource allocation strategies. The comparison results suggest that the proposed resource allocation strategy performs better than others in the perspective of utility and resource effectiveness.

cs.GT↗

arXiv2019

Redundant Loads: A Software Inefficiency Indicator

Modern software packages have become increasingly complex with millions of lines of code and references to many external libraries. Redundant operations are a common performance limiter in these code bases. Missed compiler optimization opportunities, inappropriate data structure and algorithm choices, and developers' inattention to performance are some common reasons for the existence of redundant operations. Developers mainly depend on compilers to eliminate redundant operations. However, compilers' static analysis often misses optimization opportunities due to ambiguities and limited analysis scope; automatic optimizations to algorithmic and data structural problems are out of scope. We develop LoadSpy, a whole-program profiler to pinpoint redundant memory load operations, which are often a symptom of many redundant operations. The strength of LoadSpy exists in identifying and quantifying redundant load operations in programs and associating the redundancies with program execution contexts and scopes to focus developers' attention on problematic code. LoadSpy works on fully optimized binaries, adopts various optimization techniques to reduce its overhead, and provides a rich graphic user interface, which make it a complete developer tool. Applying LoadSpy showed that a large fraction of redundant loads is common in modern software packages despite highest levels of automatic compiler optimizations. Guided by LoadSpy, we optimize several well-known benchmarks and real-world applications, yielding significant speedups.

cs.PF↗

arXiv2019

Energy-Time Entanglement-based Dispersive Optics Quantum Key Distribution over Optical Fibers of 20 km

An energy-time entanglement-based dispersive optics quantum key distribution (DO-QKD) is demonstrated experimentally over optical fibers of 20 km. In the experiment, the telecom band energy-time entangled photon pairs are generated through spontaneous four wave mixing in a silicon waveguide. The arrival time of photons are registered for key generating and security test. High dimensional encoding in the arrival time of photons is used to increase the information per coincidence of photon pairs. The bin sifting process is optimized by a three level structure, which significantly reduces the raw quantum bit error rate (QBER) due to timing jitters of detectors and electronics. A raw key generation rate of 151kbps with QBER of 4.95% is achieved, under a time-bin encoding format with 4 bits per coincidence. This experiment shows that entanglement-based DO-QKD can be implemented in an efficient and convenient way, which has great potential in quantum secure communication networks in the future.

quant-ph↗