arXiv subjects

Lei He

Publications and source records attributed to Lei He.

At least 145 records · Page 8Linked to original sources

arXiv2021

LW-GCN: A Lightweight FPGA-based Graph Convolutional Network Accelerator

Graph convolutional networks (GCNs) have been introduced to effectively process non-euclidean graph data. However, GCNs incur large amounts of irregularity in computation and memory access, which prevents efficient use of traditional neural network accelerators. Moreover, existing dedicated GCN accelerators demand high memory volumes and are difficult to implement onto resource limited edge devices. In this work, we propose LW-GCN, a lightweight FPGA-based accelerator with a software-hardware co-designed process to tackle irregularity in computation and memory access in GCN inference. LW-GCN decomposes the main GCN operations into sparse-dense matrix multiplication (SDMM) and dense matrix multiplication (DMM). We propose a novel compression format to balance workload across PEs and prevent data hazards. Moreover, we apply data quantization and workload tiling, and map both SDMM and DMM of GCN inference onto a uniform architecture on resource limited hardware. Evaluation on GCN and GraphSAGE are performed on Xilinx Kintex-7 FPGA with three popular datasets. Compared to existing CPU, GPU, and state-of-the-art FPGA-based accelerator, LW-GCN reduces latency by up to 60x, 12x and 1.7x and increases power efficiency by up to 912x., 511x and 3.87x, respectively. Furthermore, compared with NVIDIA's latest edge GPU Jetson Xavier NX, LW-GCN achieves speedup and energy savings of 32x and 84x, respectively.

cs.LG↗

arXiv2021

Diff-Net: Image Feature Difference based High-Definition Map Change Detection for Autonomous Driving

Up-to-date High-Definition (HD) maps are essential for self-driving cars. To achieve constantly updated HD maps, we present a deep neural network (DNN), Diff-Net, to detect changes in them. Compared to traditional methods based on object detectors, the essential design in our work is a parallel feature difference calculation structure that infers map changes by comparing features extracted from the camera and rasterized images. To generate these rasterized images, we project map elements onto images in the camera view, yielding meaningful map representations that can be consumed by a DNN accordingly. As we formulate the change detection task as an object detection problem, we leverage the anchor-based structure that predicts bounding boxes with different change status categories. To the best of our knowledge, the proposed method is the first end-to-end network that tackles the high-definition map change detection task, yielding a single stage solution. Furthermore, rather than relying on single frame input, we introduce a spatio-temporal fusion module that fuses features from history frames into the current, thus improving the overall performance. Finally, we comprehensively validate our method's effectiveness using freshly collected datasets. Results demonstrate that our Diff-Net achieves better performance than the baseline methods and is ready to be integrated into a map production pipeline maintaining an up-to-date HD map.

cs.CV↗

arXiv2021

Heterogeneous Dual-Core Overlay Processor for Light-Weight CNNs

Light-weight convolutional neural networks (CNNs) have small complexity and are good candidates for low-power, high-throughput inference. Such networks are heterogeneous in terms of computation-to-communication (CTC) ratios and computation patterns between layers, especially for different layer types. Yet, existing AI processors either use homogeneous processing elements (PEs), resulting in low runtime PE efficiency, or run different layers on heterogeneous PEs in sequential, introducing resource redundancy. This paper proposes a heterogeneous dual-core architecture (dual-OPU), where one core is optimized for regular convolution layers and the other for depthwise convolution layers. PEs are homogeneous with each core. To make full use of dual-core parallelism, we develop a scheduling algorithm to concurrently execute layers for different input images on dual-core and balance parallel workload. Meanwhile, we automatically tune the PE number for a core and tune the input size for each PE to maximize throughput. Compared with a single-core processor with the same area for a single network, heterogeneous dual-OPU on average improves runtime PE efficiency and throughput by 11% and 31%, respectively. For a workload of multiple networks, dual-OPU improves average throughput by 11% compared with the state-of-the-art processors scaled to the same area. To the best of our knowledge, it is the first in-depth study on the heterogeneous dual-core processor for light-weight CNNs.

cs.AR↗

arXiv2021

Speech BERT Embedding For Improving Prosody in Neural TTS

This paper presents a speech BERT model to extract embedded prosody information in speech segments for improving the prosody of synthesized speech in neural text-to-speech (TTS). As a pre-trained model, it can learn prosody attributes from a large amount of speech data, which can utilize more data than the original training data used by the target TTS. The embedding is extracted from the previous segment of a fixed length in the proposed BERT. The extracted embedding is then used together with the mel-spectrogram to predict the following segment in the TTS decoder. Experimental results obtained by the Transformer TTS show that the proposed BERT can extract fine-grained, segment-level prosody, which is complementary to utterance-level prosody to improve the final prosody of the TTS speech. The objective distortions measured on a single speaker TTS are reduced between the generated speech and original recordings. Subjective listening tests also show that the proposed approach is favorably preferred over the TTS without the BERT prosody embedding module, for both in-domain and out-of-domain applications. For Microsoft professional, single/multiple speakers and the LJ Speaker in the public database, subjective preference is similarly confirmed with the new BERT prosody embedding. TTS demo audio samples are in https://judy44chen.github.io/TTSSpeechBERT/.

eess.AS↗

arXiv2021

X2Teeth: 3D Teeth Reconstruction from a Single Panoramic Radiograph

3D teeth reconstruction from X-ray is important for dental diagnosis and many clinical operations. However, no existing work has explored the reconstruction of teeth for a whole cavity from a single panoramic radiograph. Different from single object reconstruction from photos, this task has the unique challenge of constructing multiple objects at high resolutions. To conquer this task, we develop a novel ConvNet X2Teeth that decomposes the task into teeth localization and single-shape estimation. We also introduce a patch-based training strategy, such that X2Teeth can be end-to-end trained for optimal performance. Extensive experiments show that our method can successfully estimate the 3D structure of the cavity and reflect the details for each tooth. Moreover, X2Teeth achieves a reconstruction IoU of 0.681, which significantly outperforms the encoder-decoder method by $1.71X and the retrieval-based method by $1.52X. Our method can also be promising for other multi-anatomy 3D reconstruction tasks.

cs.CV↗

arXiv2021

Cross-speaker Style Transfer with Prosody Bottleneck in Neural Speech Synthesis

Cross-speaker style transfer is crucial to the applications of multi-style and expressive speech synthesis at scale. It does not require the target speakers to be experts in expressing all styles and to collect corresponding recordings for model training. However, the performances of existing style transfer methods are still far behind real application needs. The root causes are mainly twofold. Firstly, the style embedding extracted from single reference speech can hardly provide fine-grained and appropriate prosody information for arbitrary text to synthesize. Secondly, in these models the content/text, prosody, and speaker timbre are usually highly entangled, it's therefore not realistic to expect a satisfied result when freely combining these components, such as to transfer speaking style between speakers. In this paper, we propose a cross-speaker style transfer text-to-speech (TTS) model with explicit prosody bottleneck. The prosody bottleneck builds up the kernels accounting for speaking style robustly, and disentangles the prosody from content and speaker timbre, therefore guarantees high quality cross-speaker style transfer. Evaluation result shows the proposed method even achieves on-par performance with source speaker's speaker-dependent (SD) model in objective measurement of prosody, and significantly outperforms the cycle consistency and GMVAE-based baselines in objective and subjective evaluations.

cs.SD↗

arXiv2021

TumorCP: A Simple but Effective Object-Level Data Augmentation for Tumor Segmentation

Deep learning models are notoriously data-hungry. Thus, there is an urging need for data-efficient techniques in medical image analysis, where well-annotated data are costly and time consuming to collect. Motivated by the recently revived "Copy-Paste" augmentation, we propose TumorCP, a simple but effective object-level data augmentation method tailored for tumor segmentation. TumorCP is online and stochastic, providing unlimited augmentation possibilities for tumors' subjects, locations, appearances, as well as morphologies. Experiments on kidney tumor segmentation task demonstrate that TumorCP surpasses the strong baseline by a remarkable margin of 7.12% on tumor Dice. Moreover, together with image-level data augmentation, it beats the current state-of-the-art by 2.32% on tumor Dice. Comprehensive ablation studies are performed to validate the effectiveness of TumorCP. Meanwhile, we show that TumorCP can lead to striking improvements in extremely low-data regimes. Evaluated with only 10% labeled data, TumorCP significantly boosts tumor Dice by 21.87%. To the best of our knowledge, this is the very first work exploring and extending the "Copy-Paste" design in medical imaging domain. Code is available at: https://github.com/YaoZhang93/TumorCP.

cs.CV↗

arXiv2021

On Addressing Practical Challenges for RNN-Transducer

In this paper, several works are proposed to address practical challenges for deploying RNN Transducer (RNN-T) based speech recognition system. These challenges are adapting a well-trained RNN-T model to a new domain without collecting the audio data, obtaining time stamps and confidence scores at word level. The first challenge is solved with a splicing data method which concatenates the speech segments extracted from the source domain data. To get the time stamp, a phone prediction branch is added to the RNN-T model by sharing the encoder for the purpose of force alignment. Finally, we obtain word-level confidence scores by utilizing several types of features calculated during decoding and from confusion network. Evaluated with Microsoft production data, the splicing data adaptation method improves the baseline and adaptation with the text to speech method by 58.03% and 15.25% relative word error rate reduction, respectively. The proposed time stamping method can get less than 50ms word timing difference from the ground truth alignment on average while maintaining the recognition accuracy of the RNN-T model. We also obtain high confidence annotation performance with limited computation cost.

eess.AS↗

arXiv2021

Multilingual Byte2Speech Models for Scalable Low-resource Speech Synthesis

To scale neural speech synthesis to various real-world languages, we present a multilingual end-to-end framework that maps byte inputs to spectrograms, thus allowing arbitrary input scripts. Besides strong results on 40+ languages, the framework demonstrates capabilities to adapt to new languages under extreme low-resource and even few-shot scenarios of merely 40s transcribed recording, without the need of per-language resources like lexicon, extra corpus, auxiliary models, or linguistic expertise, thus ensuring scalability. While it retains satisfactory intelligibility and naturalness matching rich-resource models. Exhaustive comparative and ablation studies are performed to reveal the potential of the framework for low-resource languages. Furthermore, we propose a novel method to extract language-specific sub-networks in a multilingual model for a better understanding of its mechanism.

cs.CL↗

arXiv2021

NPE: An FPGA-based Overlay Processor for Natural Language Processing

In recent years, transformer-based models have shown state-of-the-art results for Natural Language Processing (NLP). In particular, the introduction of the BERT language model brought with it breakthroughs in tasks such as question answering and natural language inference, advancing applications that allow humans to interact naturally with embedded devices. FPGA-based overlay processors have been shown as effective solutions for edge image and video processing applications, which mostly rely on low precision linear matrix operations. In contrast, transformer-based NLP techniques employ a variety of higher precision nonlinear operations with significantly higher frequency. We present NPE, an FPGA-based overlay processor that can efficiently execute a variety of NLP models. NPE offers software-like programmability to the end user and, unlike FPGA designs that implement specialized accelerators for each nonlinear function, can be upgraded for future NLP models without requiring reconfiguration. We demonstrate that NPE can meet real-time conversational AI latency targets for the BERT language model with $4\times$ lower power than CPUs and $6\times$ lower power than GPUs. We also show NPE uses $3\times$ fewer FPGA resources relative to comparable BERT network-specific accelerators in the literature. NPE provides a cost-effective and power-efficient FPGA-based solution for Natural Language Processing at the edge.

cs.AR↗

arXiv2021

Exploring Machine Speech Chain for Domain Adaptation and Few-Shot Speaker Adaptation

Machine Speech Chain, which integrates both end-to-end (E2E) automatic speech recognition (ASR) and text-to-speech (TTS) into one circle for joint training, has been proven to be effective in data augmentation by leveraging large amounts of unpaired data. In this paper, we explore the TTS->ASR pipeline in speech chain to do domain adaptation for both neural TTS and E2E ASR models, with only text data from target domain. We conduct experiments by adapting from audiobook domain (LibriSpeech) to presentation domain (TED-LIUM), there is a relative word error rate (WER) reduction of 10% for the E2E ASR model on the TED-LIUM test set, and a relative WER reduction of 51.5% in synthetic speech generated by neural TTS in the presentation domain. Further, we apply few-shot speaker adaptation for the E2E ASR by using a few utterances from target speakers in an unsupervised way, results in additional gains.

cs.CL↗

arXiv2021

Exploring Instance-Level Uncertainty for Medical Detection

The ability of deep learning to predict with uncertainty is recognized as key for its adoption in clinical routines. Moreover, performance gain has been enabled by modelling uncertainty according to empirical evidence. While previous work has widely discussed the uncertainty estimation in segmentation and classification tasks, its application on bounding-box-based detection has been limited, mainly due to the challenge of bounding box aligning. In this work, we explore to augment a 2.5D detection CNN with two different bounding-box-level (or instance-level) uncertainty estimates, i.e., predictive variance and Monte Carlo (MC) sample variance. Experiments are conducted for lung nodule detection on LUNA16 dataset, a task where significant semantic ambiguities can exist between nodules and non-nodules. Results show that our method improves the evaluating score from 84.57% to 88.86% by utilizing a combination of both types of variances. Moreover, we show the generated uncertainty enables superior operating points compared to using the probability threshold only, and can further boost the performance to 89.52%. Example nodule detections are visualized to further illustrate the advantages of our method.

cs.CV↗

arXiv2021

Explainable Deep Reinforcement Learning for UAV Autonomous Navigation

Autonomous navigation in unknown complex environment is still a hard problem, especially for small Unmanned Aerial Vehicles (UAVs) with limited computation resources. In this paper, a neural network-based reactive controller is proposed for a quadrotor to fly autonomously in unknown outdoor environment. The navigation controller makes use of only current sensor data to generate the control signal without any optimization or configuration space searching, which reduces both memory and computation requirement. The navigation problem is modelled as a Markov Decision Process (MDP) and solved using deep reinforcement learning (DRL) method. Specifically, to get better understanding of the trained network, some model explanation methods are proposed. Based on the feature attribution, each decision making result during flight is explained using both visual and texture explanation. Moreover, some global analysis are also provided for experts to evaluate and improve the trained neural network. The simulation results illustrated the proposed method can make useful and reasonable explanation for the trained model, which is beneficial for both non-expert users and controller designer. Finally, the real world tests shown the proposed controller can navigate the quadrotor to goal position successfully and the reactive controller performs much faster than some conventional approach under the same computation resource.

cs.RO↗

arXiv2021

Atlas-aware ConvNetfor Accurate yet Robust Anatomical Segmentation

Convolutional networks (ConvNets) have achieved promising accuracy for various anatomical segmentation tasks. Despite the success, these methods can be sensitive to data appearance variations. Considering the large variability of scans caused by artifacts, pathologies, and scanning setups, robust ConvNets are vital for clinical applications, while have not been fully explored. In this paper, we propose to mitigate the challenge by enabling ConvNets' awareness of the underlying anatomical invariances among imaging scans. Specifically, we introduce a fully convolutional Constraint Adoption Module (CAM) that incorporates probabilistic atlas priors as explicit constraints for predictions over a locally connected Conditional Random Field (CFR), which effectively reinforces the anatomical consistency of the labeling outputs. We design the CAM to be flexible for boosting various ConvNet, and compact for co-optimizing with ConvNets for fusion parameters that leads to the optimal performance. We show the advantage of such atlas priors fusion is two-fold with two brain parcellation tasks. First, our models achieve state-of-the-art accuracy among ConvNet-based methods on both datasets, by significantly reducing structural abnormalities of predictions. Second, we can largely boost the robustness of existing ConvNets, proved by: (i) testing on scans with synthetic pathologies, and (ii) training and evaluation on scans of different scanning setups across datasets. Our method is proposing to be easily adopted to existing ConvNets by fine-tuning with CAM plugged in for accuracy and robustness boosts.

cs.CV↗

arXiv2021

SOSD-Net: Joint Semantic Object Segmentation and Depth Estimation from Monocular images

Depth estimation and semantic segmentation play essential roles in scene understanding. The state-of-the-art methods employ multi-task learning to simultaneously learn models for these two tasks at the pixel-wise level. They usually focus on sharing the common features or stitching feature maps from the corresponding branches. However, these methods lack in-depth consideration on the correlation of the geometric cues and the scene parsing. In this paper, we first introduce the concept of semantic objectness to exploit the geometric relationship of these two tasks through an analysis of the imaging process, then propose a Semantic Object Segmentation and Depth Estimation Network (SOSD-Net) based on the objectness assumption. To the best of our knowledge, SOSD-Net is the first network that exploits the geometry constraint for simultaneous monocular depth estimation and semantic segmentation. In addition, considering the mutual implicit relationship between these two tasks, we exploit the iterative idea from the expectation-maximization algorithm to train the proposed network more effectively. Extensive experimental results on the Cityscapes and NYU v2 dataset are presented to demonstrate the superior performance of the proposed approach.

cs.CV↗

arXiv2021

T-Net: Learning Feature Representation with Task-specific Supervision for Biomedical Image Analysis

The encoder-decoder network is widely used to learn deep feature representations from pixel-wise annotations in biomedical image analysis. Under this structure, the performance profoundly relies on the effectiveness of feature extraction achieved by the encoding network. However, few models have considered adapting the attention of the feature extractor even in different kinds of tasks. In this paper, we propose a novel training strategy by adapting the attention of the feature extractor according to different tasks for effective representation learning. Specifically, the framework, named T-Net, consists of an encoding network supervised by task-specific attention maps and a posterior network that takes in the learned features to predict the corresponding results. The attention map is obtained by the transformation from pixel-wise annotations according to the specific task, which is used as the supervision to regularize the feature extractor to focus on different locations of the recognition object. To show the effectiveness of our method, we evaluate T-Net on two different tasks, i.e. , segmentation and localization. Extensive results on three public datasets (BraTS-17, MoNuSeg and IDRiD) have indicated the effectiveness and efficiency of our proposed supervision method, especially over the conventional encoding-decoding network.

eess.IV↗

arXiv2021

Oral-3D: Reconstructing the 3D Bone Structure of Oral Cavity from 2D Panoramic X-ray

Panoramic X-ray (PX) provides a 2D picture of the patient's mouth in a panoramic view to help dentists observe the invisible disease inside the gum. However, it provides limited 2D information compared with cone-beam computed tomography (CBCT), another dental imaging method that generates a 3D picture of the oral cavity but with more radiation dose and a higher price. Consequently, it is of great interest to reconstruct the 3D structure from a 2D X-ray image, which can greatly explore the application of X-ray imaging in dental surgeries. In this paper, we propose a framework, named Oral-3D, to reconstruct the 3D oral cavity from a single PX image and prior information of the dental arch. Specifically, we first train a generative model to learn the cross-dimension transformation from 2D to 3D. Then we restore the shape of the oral cavity with a deformation module with the dental arch curve, which can be obtained simply by taking a photo of the patient's mouth. To be noted, Oral-3D can restore both the density of bony tissues and the curved mandible surface. Experimental results show that Oral-3D can efficiently and effectively reconstruct the 3D oral structure and show critical information in clinical applications, e.g., tooth pulling and dental implants. To the best of our knowledge, we are the first to explore this domain transformation problem between these two imaging methods.

eess.IV↗

arXiv2020

OralViewer: 3D Demonstration of Dental Surgeries for Patient Education with Oral Cavity Reconstruction from a 2D Panoramic X-ray

Patient's understanding on forthcoming dental surgeries is required by patient-centered care and helps reduce fear and anxiety. Due to the gap of expertise between patients and dentists, conventional techniques of patient education are usually not effective for explaining surgical steps. In this paper, we present \textit{OralViewer} -- the first interactive application that enables dentist's demonstration of dental surgeries in 3D to promote patients' understanding. \textit{OralViewer} takes a single 2D panoramic dental X-ray to reconstruct patient-specific 3D teeth structures, which are then assembled with registered gum and jaw bone models for complete oral cavity modeling. During the demonstration, \textit{OralViewer} enables dentists to show surgery steps with virtual dental instruments that can animate effects on a 3D model in real-time. A technical evaluation shows our deep learning based model achieves a mean Intersection over Union (IoU) of 0.771 for 3D teeth reconstruction. A patient study with 12 participants shows \textit{OralViewer} can improve patients' understanding of surgeries. An expert study with 3 board-certified dentists further verifies the clinical validity of our system.

cs.HC↗