arXiv subjects

Hao Chen

Publications and source records attributed to Hao Chen.

At least 1,351 records · Page 75Linked to original sources

arXiv2019

PRSNet: Part Relation and Selection Network for Bone Age Assessment

Bone age is one of the most important indicators for assessing bone's maturity, which can help to interpret human's growth development level and potential progress. In the clinical practice, bone age assessment (BAA) of X-ray images requires the joint consideration of the appearance and location information of hand bones. These kinds of information can be effectively captured by the relation of different anatomical parts of hand bone. Recently developed methods differ mostly in how they model the part relation and choose useful parts for BAA. However, these methods neglect the mining of relationship among different parts, which can help to improve the assessment accuracy. In this paper, we propose a novel part relation module, which accurately discovers the underlying concurrency of parts by using multi-scale context information of deep learning feature representation. Furthermore, based on the part relation, we explore a new part selection module, which comprehensively measures the importance of parts and select the top ranking parts for assisting BAA. We jointly train our part relation and selection modules in an end-to-end way, achieving state-of-the-art performance on the public RSNA 2017 Pediatric Bone Age benchmark dataset and outperforming other competitive methods by a significant margin.

cs.CV↗

arXiv2019

Combined Task and Motion Planning for a Dual-arm Robot to Use a Suction Cup Tool

This paper proposes a combined task and motion planner for a dual-arm robot to use a suction cup tool. The planner consists of three sub-planners -- A suction pose sub-planner and two regrasp and motion sub-planners. The suction pose sub-planner finds all the available poses for a suction cup tool to suck on the object, using the models of the tool and the object. The regrasp and motion sub-planner builds the regrasp graph that represents all possible grasp sequences to reorient and move the suction cup tool from an initial pose to a goal pose. Two regrasp graphs are used to plan for a single suction cup and the complex of the suction cup and an object respectively. The output of the proposed planner is a sequence of robot motion that uses a suction cup tool to manipulate objects following human instructions. The planner is examined and analyzed by both simulation experiments and real-world executions using several real-world tasks. The results show that the planner is efficient, robust, and can generate sequential transit and transfer robot motion to finish complicated combined task and motion planning tasks in a few seconds.

cs.RO↗

arXiv2019

FCOS: Fully Convolutional One-Stage Object Detection

We propose a fully convolutional one-stage object detector (FCOS) to solve object detection in a per-pixel prediction fashion, analogue to semantic segmentation. Almost all state-of-the-art object detectors such as RetinaNet, SSD, YOLOv3, and Faster R-CNN rely on pre-defined anchor boxes. In contrast, our proposed detector FCOS is anchor box free, as well as proposal free. By eliminating the predefined set of anchor boxes, FCOS completely avoids the complicated computation related to anchor boxes such as calculating overlapping during training. More importantly, we also avoid all hyper-parameters related to anchor boxes, which are often very sensitive to the final detection performance. With the only post-processing non-maximum suppression (NMS), FCOS with ResNeXt-64x4d-101 achieves 44.7% in AP with single-model and single-scale testing, surpassing previous one-stage detectors with the advantage of being much simpler. For the first time, we demonstrate a much simpler and flexible detection framework achieving improved detection accuracy. We hope that the proposed FCOS framework can serve as a simple and strong alternative for many other instance-level tasks. Code is available at:Code is available at: https://tinyurl.com/FCOSv1

cs.CV↗

arXiv2019

IRNet: Instance Relation Network for Overlapping Cervical Cell Segmentation

Cell instance segmentation in Pap smear image remains challenging due to the wide existence of occlusion among translucent cytoplasm in cell clumps. Conventional methods heavily rely on accurate nuclei detection results and are easily disturbed by miscellaneous objects. In this paper, we propose a novel Instance Relation Network (IRNet) for robust overlapping cell segmentation by exploring instance relation interaction. Specifically, we propose the Instance Relation Module to construct the cell association matrix for transferring information among individual cell-instance features. With the collaboration of different instances, the augmented features gain benefits from contextual information and improve semantic consistency. Meanwhile, we proposed a sparsity constrained Duplicate Removal Module to eliminate the misalignment between classification and localization accuracy for candidates selection. The largest cervical Pap smear (CPS) dataset with more than 8000 cell annotations in Pap smear image was constructed for comprehensive evaluation. Our method outperforms other methods by a large margin, demonstrating the effectiveness of exploring instance relation.

cs.CV↗

arXiv2019

Detecting 11K Classes: Large Scale Object Detection without Fine-Grained Bounding Boxes

Recent advances in deep learning greatly boost the performance of object detection. State-of-the-art methods such as Faster-RCNN, FPN and R-FCN have achieved high accuracy in challenging benchmark datasets. However, these methods require fully annotated object bounding boxes for training, which are incredibly hard to scale up due to the high annotation cost. Weakly-supervised methods, on the other hand, only require image-level labels for training, but the performance is far below their fully-supervised counterparts. In this paper, we propose a semi-supervised large scale fine-grained detection method, which only needs bounding box annotations of a smaller number of coarse-grained classes and image-level labels of large scale fine-grained classes, and can detect all classes at nearly fully-supervised accuracy. We achieve this by utilizing the correlations between coarse-grained and fine-grained classes with shared backbone, soft-attention based proposal re-ranking, and a dual-level memory module. Experiment results show that our methods can achieve close accuracy on object detection to state-of-the-art fully-supervised methods on two large scale datasets, ImageNet and OpenImages, with only a small fraction of fully annotated classes.

cs.CV↗

arXiv2019

Sequential Computer Experimental Design for Estimating an Extreme Probability or Quantile

A computer code can simulate a system's propagation of variation from random inputs to output measures of quality. Our aim here is to estimate a critical output tail probability or quantile without a large Monte Carlo experiment. Instead, we build a statistical surrogate for the input-output relationship with a modest number of evaluations and then sequentially add further runs, guided by a criterion to improve the estimate. We compare two criteria in the literature. Moreover, we investigate two practical questions: how to design the initial code runs and how to model the input distribution. Hence, we close the gap between the theory of sequential design and its application.

stat.ML↗

arXiv2019

Surpassing the rate-transmittance linear bound of quantum key distribution

Quantum key distribution (QKD offers a long-term solution to establish information-theoretically secure keys between two distant users. In practice, with a careful characterization of quantum sources and the decoy-state method, measure-device-independent quantum key distribution (MDI-QKD) provides secure key distribution. While short-distance fibre-based QKD has already been available for real-life implementation, the bottleneck of practical QKD lies on the limited transmission distance. Due to photon losses in transmission, it was believed that the key generation rate is bounded by a linear function of the channel transmittance, $O(η)$, without a quantum repeater, which puts an upper bound on the maximal secure transmission distance. Interestingly, a new phase-encoding MDI-QKD scheme, named twin-field QKD, has been suggested to beat the linear bound, while another variant, named phase-matching quantum key distribution (PM-QKD), has been proven to have a quadratic key-rate improvement, $O(\sqrtη)$. In reality, however, the intrinsic optical mode mismatch of independent lasers, accompanied by phase fluctuation and drift, impedes the successful experimental implementation of the new schemes. Here, we solve this problem with the assistance of the laser injection technique and the phase post-compensation method. In the experiment, the key rate surpasses the linear key-rate bound via 302 km and 402 km commercial-fibre channels, achieving a key rate over 4 orders of magnitude higher than the existing results in literature. Furthermore, with a 502 km ultralow-loss fibre, our system yields a secret key rate of 0.118 bps. We expect this new type of QKD schemes to become a new standard for future QKD.

quant-ph↗

arXiv2019

Unifying Structure Analysis and Surrogate-driven Function Regression for Glaucoma OCT Image Screening

Optical Coherence Tomography (OCT) imaging plays an important role in glaucoma diagnosis in clinical practice. Early detection and timely treatment can prevent glaucoma patients from permanent vision loss. However, only a dearth of automated methods has been developed based on OCT images for glaucoma study. In this paper, we present a novel framework to effectively classify glaucoma OCT images from normal ones. A semi-supervised learning strategy with smoothness assumption is applied for surrogate assignment of missing function regression labels. Besides, the proposed multi-task learning network is capable of exploring the structure and function relationship from the OCT image and visual field measurement simultaneously, which contributes to classification performance boosting. Essentially, we are the first to unify the structure analysis and function regression for glaucoma screening. It is also worth noting that we build the largest glaucoma OCT image dataset involving 4877 volumes to develop and evaluate the proposed method. Extensive experiments demonstrate that our framework outperforms the baseline methods and two glaucoma experts by a large margin, achieving 93.2%, 93.2% and 97.8% on accuracy, F1 score and AUC, respectively.

cs.CV↗

arXiv2019

Artificial Intelligence-Enabled Cellular Networks: A Critical Path to Beyond-5G and 6G

Mobile Network Operators (MNOs) are in process of overlaying their conventional macro cellular networks with shorter range cells such as outdoor pico cells. The resultant increase in network complexity creates substantial overhead in terms of operating expenses, time, and labor for their planning and management. Artificial intelligence (AI) offers the potential for MNOs to operate their networks in a more organic and cost-efficient manner. We argue that deploying AI in 5G and Beyond will require surmounting significant technical barriers in terms of robustness, performance, and complexity. We outline future research directions, identify top 5 challenges, and present a possible roadmap to realize the vision of AI-enabled cellular networks for Beyond-5G and 6G.

cs.IT↗

arXiv2019

PFA-ScanNet: Pyramidal Feature Aggregation with Synergistic Learning for Breast Cancer Metastasis Analysis

Automatic detection of cancer metastasis from whole slide images (WSIs) is a crucial step for following patient staging and prognosis. Recent convolutional neural network based approaches are struggling with the trade-off between accuracy and computational efficiency due to the difficulty in processing large-scale gigapixel WSIs. To meet this challenge, we propose a novel Pyramidal Feature Aggregation ScanNet (PFA-ScanNet) for robust and fast analysis of breast cancer metastasis. Our method mainly benefits from the aggregation of extracted local-to-global features with diverse receptive fields, as well as the proposed synergistic learning for training the main detector and extra decoder with semantic guidance. Furthermore, a high-efficiency inference mechanism is designed with dense pooling layers, which allows dense and fast scanning for gigapixel WSI analysis. As a result, the proposed PFA-ScanNet achieved the state-of-the-art FROC of 90.2% on the Camelyon16 dataset, as well as competitive kappa score of 0.905 on the Camelyon17 leaderboard. In addition, our method shows leading speed advantage over other methods, about 7.2 min per WSI with a single GPU, making automatic analysis of breast cancer metastasis more applicable in the clinical usage.

cs.CV↗

arXiv2019

Multi-Task Recurrent Convolutional Network with Correlation Loss for Surgical Video Analysis

Surgical tool presence detection and surgical phase recognition are two fundamental yet challenging tasks in surgical video analysis and also very essential components in various applications in modern operating rooms. While these two analysis tasks are highly correlated in clinical practice as the surgical process is well-defined, most previous methods tackled them separately, without making full use of their relatedness. In this paper, we present a novel method by developing a multi-task recurrent convolutional network with correlation loss (MTRCNet-CL) to exploit their relatedness to simultaneously boost the performance of both tasks. Specifically, our proposed MTRCNet-CL model has an end-to-end architecture with two branches, which share earlier feature encoders to extract general visual features while holding respective higher layers targeting for specific tasks. Given that temporal information is crucial for phase recognition, long-short term memory (LSTM) is explored to model the sequential dependencies in the phase recognition branch. More importantly, a novel and effective correlation loss is designed to model the relatedness between tool presence and phase identification of each video frame, by minimizing the divergence of predictions from the two branches. Mutually leveraging both low-level feature sharing and high-level prediction correlating, our MTRCNet-CL method can encourage the interactions between the two tasks to a large extent, and hence can bring about benefits to each other. Extensive experiments on a large surgical video dataset (Cholec80) demonstrate outstanding performance of our proposed method, consistently exceeding the state-of-the-art methods by a large margin (e.g., 89.1% v.s. 81.0% for the mAP in tool presence detection and 87.4% v.s. 84.5% for F1 score in phase recognition). The code can be found on our project website.

cs.CV↗

arXiv2019

Synergistic Image and Feature Adaptation: Towards Cross-Modality Domain Adaptation for Medical Image Segmentation

This paper presents a novel unsupervised domain adaptation framework, called Synergistic Image and Feature Adaptation (SIFA), to effectively tackle the problem of domain shift. Domain adaptation has become an important and hot topic in recent studies on deep learning, aiming to recover performance degradation when applying the neural networks to new testing domains. Our proposed SIFA is an elegant learning diagram which presents synergistic fusion of adaptations from both image and feature perspectives. In particular, we simultaneously transform the appearance of images across domains and enhance domain-invariance of the extracted features towards the segmentation task. The feature encoder layers are shared by both perspectives to grasp their mutual benefits during the end-to-end learning procedure. Without using any annotation from the target domain, the learning of our unified model is guided by adversarial losses, with multiple discriminators employed from various aspects. We have extensively validated our method with a challenging application of cross-modality medical image segmentation of cardiac structures. Experimental results demonstrate that our SIFA model recovers the degraded performance from 17.2% to 73.0%, and outperforms the state-of-the-art methods by a significant margin.

cs.CV↗

arXiv2019

Self-Tuning Sectorization: Deep Reinforcement Learning Meets Broadcast Beam Optimization

Beamforming in multiple input multiple output (MIMO) systems is one of the key technologies for modern wireless communication. Creating appropriate sector-specific broadcast beams are essential for enhancing the coverage of cellular network and for improving the broadcast operation for control signals. However, in order to maximize the coverage, patterns for broadcast beams need to be adapted based on the users' distribution and movement over time. In this work, we present self-tuning sectorization: a deep reinforcement learning framework to optimize MIMO broadcast beams autonomously and dynamically based on user' distribution in the network. Taking directly UE measurement results as input, deep reinforcement learning agent can track and predict the UE distribution pattern and come up with the best broadcast beams for each cell. Extensive simulation results show that the introduced framework can achieve the optimal coverage, and converge to the oracle solution for both single sector and multiple sectors environment, and for both periodic and Markov mobility patterns.

eess.SP↗

arXiv2019

Deep Angular Embedding and Feature Correlation Attention for Breast MRI Cancer Analysis

Accurate and automatic analysis of breast MRI plays an important role in early diagnosis and successful treatment planning for breast cancer. Due to the heterogeneity nature, accurate diagnosis of tumors remains a challenging task. In this paper, we propose to identify breast tumor in MRI by Cosine Margin Sigmoid Loss (CMSL) with deep learning (DL) and localize possible cancer lesion by COrrelation Attention Map (COAM) based on the learned features. The CMSL embeds tumor features onto a hypersphere and imposes a decision margin through cosine constraints. In this way, the DL model could learn more separable inter-class features and more compact intra-class features in the angular space. Furthermore, we utilize the correlations among feature vectors to generate attention maps that could accurately localize cancer candidates with only image-level label. We build the largest breast cancer dataset involving 10,290 DCE-MRI scan volumes for developing and evaluating the proposed methods. The model driven by CMSL achieved classification accuracy of 0.855 and AUC of 0.902 on the testing set, with sensitivity and specificity of 0.857 and 0.852, respectively, outperforming other competitive methods overall. In addition, the proposed COAM accomplished more accurate localization of the cancer center compared with other state-of-the-art weakly supervised localization method.

eess.IV↗

arXiv2019

Directional Transport of Propelled Brownian Particles Confined in a Smooth Corrugated Channel with Colored Noise

The transport phenomenon(directional movement) of self-propelled Brownian particles moving in a smooth corrugated confined channel is investigated. It is found that large $x$ direction noise intensity should reduce particles directional movement when the angle Gaussian noise intensity is small. The average velocity has a maximum with increasing $x$ direction noise intensity when angle Gaussian noise intensity is large. $y$ directional noise has negligible effect on $x$ directional movement. Large angle Gaussian noise intensity should weaken the directional transport. Interestingly, the movement direction changes more than once with increasing periodic force amplitude.

cond-mat.soft↗

arXiv2019

Toward Scalable Fully Homomorphic Encryption Through Light Trusted Computing Assistance

It has been a long standing problem to securely outsource computation tasks to an untrusted party with integrity and confidentiality guarantees. While fully homomorphic encryption (FHE) is a promising technique that allows computations performed on the encrypted data, it suffers from a significant slow down to the computation. In this paper we propose a hybrid solution that uses the latest hardware Trusted Execution Environments (TEEs) to assist FHE by moving the bootstrapping step, which is one of the major obstacles in designing practical FHE schemes, to a secured SGX enclave. TEEFHE, the hybrid system we designed, makes it possible for homomorphic computations to be performed on smaller ciphertext and secret key, providing better performance and lower memory consumption. We make an effort to mitigate side channel leakages within SGX by making the memory access patterns totally independent from the secret information. The evaluation shows that TEEFHE effectively improves the software only FHE schemes in terms of both time and space.

cs.CR↗

arXiv2019

Fast Neural Architecture Search of Compact Semantic Segmentation Models via Auxiliary Cells

Automated design of neural network architectures tailored for a specific task is an extremely promising, albeit inherently difficult, avenue to explore. While most results in this domain have been achieved on image classification and language modelling problems, here we concentrate on dense per-pixel tasks, in particular, semantic image segmentation using fully convolutional networks. In contrast to the aforementioned areas, the design choices of a fully convolutional network require several changes, ranging from the sort of operations that need to be used---e.g., dilated convolutions---to a solving of a more difficult optimisation problem. In this work, we are particularly interested in searching for high-performance compact segmentation architectures, able to run in real-time using limited resources. To achieve that, we intentionally over-parameterise the architecture during the training time via a set of auxiliary cells that provide an intermediate supervisory signal and can be omitted during the evaluation phase. The design of the auxiliary cell is emitted by a controller, a neural network with the fixed structure trained using reinforcement learning. More crucially, we demonstrate how to efficiently search for these architectures within limited time and computational budgets. In particular, we rely on a progressive strategy that terminates non-promising architectures from being further trained, and on Polyak averaging coupled with knowledge distillation to speed-up the convergence. Quantitatively, in 8 GPU-days our approach discovers a set of architectures performing on-par with state-of-the-art among compact models on the semantic segmentation, pose estimation and depth prediction tasks. Code will be made available here: https://github.com/drsleep/nas-segm-pytorch

cs.CV↗

arXiv2019

A New Hierarchical Software Architecture Towards Safety-Critical Aspects of a Drone System

In this paper, a new hierarchical software architecture is proposed to improve the safety and reliability of a safety-critical drone system from the perspective of its source code. The proposed architecture uses formal verification methods to ensure that the implementation of each module satisfies its expected design specification, so that it prevents a drone from crashing due to unexpected software failures. This study builds on top of a formally verified operating system kernel, certified kit operating system (CertiKOS). Since device drivers are considered the most important parts affecting the safety of the drone system, we focus mainly on verifying bus drivers such as the serial peripheral interface and the inter-integrated circuit drivers in a drone system using a rigorous formal verification method. Experiments have been carried out to demonstrate the improvement in reliability in case of device anomalies.

cs.SE↗