arXiv subjects

Rui Zhao

Publications and source records attributed to Rui Zhao.

At least 289 records · Page 16Linked to original sources

arXiv2020

Developing RNN-T Models Surpassing High-Performance Hybrid Models with Customization Capability

Because of its streaming nature, recurrent neural network transducer (RNN-T) is a very promising end-to-end (E2E) model that may replace the popular hybrid model for automatic speech recognition. In this paper, we describe our recent development of RNN-T models with reduced GPU memory consumption during training, better initialization strategy, and advanced encoder modeling with future lookahead. When trained with Microsoft's 65 thousand hours of anonymized training data, the developed RNN-T model surpasses a very well trained hybrid model with both better recognition accuracy and lower latency. We further study how to customize RNN-T models to a new domain, which is important for deploying E2E models to practical scenarios. By comparing several methods leveraging text-only data in the new domain, we found that updating RNN-T's prediction and joint networks using text-to-speech generated from domain-specific text is the most effective.

eess.AS↗

arXiv2020

Self-supervising Fine-grained Region Similarities for Large-scale Image Localization

The task of large-scale retrieval-based image localization is to estimate the geographical location of a query image by recognizing its nearest reference images from a city-scale dataset. However, the general public benchmarks only provide noisy GPS labels associated with the training images, which act as weak supervisions for learning image-to-image similarities. Such label noise prevents deep neural networks from learning discriminative features for accurate localization. To tackle this challenge, we propose to self-supervise image-to-region similarities in order to fully explore the potential of difficult positive images alongside their sub-regions. The estimated image-to-region similarities can serve as extra training supervision for improving the network in generations, which could in turn gradually refine the fine-grained similarities to achieve optimal performance. Our proposed self-enhanced image-to-region similarity labels effectively deal with the training bottleneck in the state-of-the-art pipelines without any additional parameters or manual annotations in both training and inference. Our method outperforms state-of-the-arts on the standard localization benchmarks by noticeable margins and shows excellent generalization capability on multiple image retrieval datasets.

cs.CV↗

arXiv2020

Learning Individualized Treatment Rules with Estimated Translated Inverse Propensity Score

Randomized controlled trials typically analyze the effectiveness of treatments with the goal of making treatment recommendations for patient subgroups. With the advance of electronic health records, a great variety of data has been collected in clinical practice, enabling the evaluation of treatments and treatment policies based on observational data. In this paper, we focus on learning individualized treatment rules (ITRs) to derive a treatment policy that is expected to generate a better outcome for an individual patient. In our framework, we cast ITRs learning as a contextual bandit problem and minimize the expected risk of the treatment policy. We conduct experiments with the proposed framework both in a simulation study and based on a real-world dataset. In the latter case, we apply our proposed method to learn the optimal ITRs for the administration of intravenous (IV) fluids and vasopressors (VP). Based on various offline evaluation methods, we could show that the policy derived in our framework demonstrates better performance compared to both the physicians and other baselines, including a simple treatment prediction approach. As a long-term goal, our derived policy might eventually lead to better clinical guidelines for the administration of IV and VP.

cs.LG↗

arXiv2020

Continual Representation Learning for Biometric Identification

With the explosion of digital data in recent years, continuously learning new tasks from a stream of data without forgetting previously acquired knowledge has become increasingly important. In this paper, we propose a new continual learning (CL) setting, namely ``continual representation learning'', which focuses on learning better representation in a continuous way. We also provide two large-scale multi-step benchmarks for biometric identification, where the visual appearance of different classes are highly relevant. In contrast to requiring the model to recognize more learned classes, we aim to learn feature representation that can be better generalized to not only previously unseen images but also unseen classes/identities. For the new setting, we propose a novel approach that performs the knowledge distillation over a large number of identities by applying the neighbourhood selection and consistency relaxation strategies to improve scalability and flexibility of the continual learning model. We demonstrate that existing CL methods can improve the representation in the new setting, and our method achieves better results than the competitors.

cs.CV↗

arXiv2020

Enhancement of a CNN-Based Denoiser Based on Spatial and Spectral Analysis

Convolutional neural network (CNN)-based image denoising methods have been widely studied recently, because of their high-speed processing capability and good visual quality. However, most of the existing CNN-based denoisers learn the image prior from the spatial domain, and suffer from the problem of spatially variant noise, which limits their performance in real-world image denoising tasks. In this paper, we propose a discrete wavelet denoising CNN (WDnCNN), which restores images corrupted by various noise with a single model. Since most of the content or energy of natural images resides in the low-frequency spectrum, their transformed coefficients in the frequency domain are highly imbalanced. To address this issue, we present a band normalization module (BNM) to normalize the coefficients from different parts of the frequency spectrum. Moreover, we employ a band discriminative training (BDT) criterion to enhance the model regression. We evaluate the proposed WDnCNN, and compare it with other state-of-the-art denoisers. Experimental results show that WDnCNN achieves promising performance in both synthetic and real noise reduction, making it a potential solution to many practical image denoising applications.

eess.IV↗

arXiv2020

Mutual Information-based State-Control for Intrinsically Motivated Reinforcement Learning

In reinforcement learning, an agent learns to reach a set of goals by means of an external reward signal. In the natural world, intelligent organisms learn from internal drives, bypassing the need for external signals, which is beneficial for a wide range of tasks. Motivated by this observation, we propose to formulate an intrinsic objective as the mutual information between the goal states and the controllable states. This objective encourages the agent to take control of its environment. Subsequently, we derive a surrogate objective of the proposed reward function, which can be optimized efficiently. Lastly, we evaluate the developed framework in different robotic manipulation and navigation tasks and demonstrate the efficacy of our approach. A video showing experimental results is available at https://youtu.be/CT4CKMWBYz0

cs.LG↗

arXiv2020

Energy-Based Hindsight Experience Prioritization

In Hindsight Experience Replay (HER), a reinforcement learning agent is trained by treating whatever it has achieved as virtual goals. However, in previous work, the experience was replayed at random, without considering which episode might be the most valuable for learning. In this paper, we develop an energy-based framework for prioritizing hindsight experience in robotic manipulation tasks. Our approach is inspired by the work-energy principle in physics. We define a trajectory energy function as the sum of the transition energy of the target object over the trajectory. We hypothesize that replaying episodes that have high trajectory energy is more effective for reinforcement learning in robotics. To verify our hypothesis, we designed a framework for hindsight experience prioritization based on the trajectory energy of goal states. The trajectory energy function takes the potential, kinetic, and rotational energy into consideration. We evaluate our Energy-Based Prioritization (EBP) approach on four challenging robotic manipulation tasks in simulation. Our empirical results show that our proposed method surpasses state-of-the-art approaches in terms of both performance and sample-efficiency on all four tasks, without increasing computational time. A video showing experimental results is available at https://youtu.be/jtsF2tTeUGQ

cs.LG↗

arXiv2020

Curiosity-Driven Experience Prioritization via Density Estimation

In Reinforcement Learning (RL), an agent explores the environment and collects trajectories into the memory buffer for later learning. However, the collected trajectories can easily be imbalanced with respect to the achieved goal states. The problem of learning from imbalanced data is a well-known problem in supervised learning, but has not yet been thoroughly researched in RL. To address this problem, we propose a novel Curiosity-Driven Prioritization (CDP) framework to encourage the agent to over-sample those trajectories that have rare achieved goal states. The CDP framework mimics the human learning process and focuses more on relatively uncommon events. We evaluate our methods using the robotic environment provided by OpenAI Gym. The environment contains six robot manipulation tasks. In our experiments, we combined CDP with Deep Deterministic Policy Gradient (DDPG) with or without Hindsight Experience Replay (HER). The experimental results show that CDP improves both performance and sample-efficiency of reinforcement learning agents, compared to state-of-the-art methods.

cs.LG↗

arXiv2020

Maximum Entropy-Regularized Multi-Goal Reinforcement Learning

In Multi-Goal Reinforcement Learning, an agent learns to achieve multiple goals with a goal-conditioned policy. During learning, the agent first collects the trajectories into a replay buffer, and later these trajectories are selected randomly for replay. However, the achieved goals in the replay buffer are often biased towards the behavior policies. From a Bayesian perspective, when there is no prior knowledge about the target goal distribution, the agent should learn uniformly from diverse achieved goals. Therefore, we first propose a novel multi-goal RL objective based on weighted entropy. This objective encourages the agent to maximize the expected return, as well as to achieve more diverse goals. Secondly, we developed a maximum entropy-based prioritization framework to optimize the proposed objective. For evaluation of this framework, we combine it with Deep Deterministic Policy Gradient, both with or without Hindsight Experience Replay. On a set of multi-goal robotic tasks of OpenAI Gym, we compare our method with other baselines and show promising improvements in both performance and sample-efficiency.

cs.LG↗

arXiv2020

Learning Goal-Oriented Visual Dialog via Tempered Policy Gradient

Learning goal-oriented dialogues by means of deep reinforcement learning has recently become a popular research topic. However, commonly used policy-based dialogue agents often end up focusing on simple utterances and suboptimal policies. To mitigate this problem, we propose a class of novel temperature-based extensions for policy gradient methods, which are referred to as Tempered Policy Gradients (TPGs). On a recent AI-testbed, i.e., the GuessWhat?! game, we achieve significant improvements with two innovations. The first one is an extension of the state-of-the-art solutions with Seq2Seq and Memory Network structures that leads to an improvement of 7%. The second one is the application of our newly developed TPG methods, which improves the performance additionally by around 5% and, even more importantly, helps produce more convincing utterances.

cs.LG↗

arXiv2020

Efficient Dialog Policy Learning via Positive Memory Retention

This paper is concerned with the training of recurrent neural networks as goal-oriented dialog agents using reinforcement learning. Training such agents with policy gradients typically requires a large amount of samples. However, the collection of the required data in form of conversations between chat-bots and human agents is time-consuming and expensive. To mitigate this problem, we describe an efficient policy gradient method using positive memory retention, which significantly increases the sample-efficiency. We show that our method is 10 times more sample-efficient than policy gradients in extensive experiments on a new synthetic number guessing game. Moreover, in a real-word visual object discovery game, the proposed method is twice as sample-efficient as policy gradients and shows state-of-the-art performance.

cs.AI↗

arXiv2020

COCAS: A Large-Scale Clothes Changing Person Dataset for Re-identification

Recent years have witnessed great progress in person re-identification (re-id). Several academic benchmarks such as Market1501, CUHK03 and DukeMTMC play important roles to promote the re-id research. To our best knowledge, all the existing benchmarks assume the same person will have the same clothes. While in real-world scenarios, it is very often for a person to change clothes. To address the clothes changing person re-id problem, we construct a novel large-scale re-id benchmark named ClOthes ChAnging Person Set (COCAS), which provides multiple images of the same identity with different clothes. COCAS totally contains 62,382 body images from 5,266 persons. Based on COCAS, we introduce a new person re-id setting for clothes changing problem, where the query includes both a clothes template and a person image taking another clothes. Moreover, we propose a two-branch network named Biometric-Clothes Network (BC-Net) which can effectively integrate biometric and clothes feature for re-id under our setting. Experiments show that it is feasible for clothes changing re-id with clothes templates.

cs.CV↗

arXiv2020

Exploring Pre-training with Alignments for RNN Transducer based End-to-End Speech Recognition

Recently, the recurrent neural network transducer (RNN-T) architecture has become an emerging trend in end-to-end automatic speech recognition research due to its advantages of being capable for online streaming speech recognition. However, RNN-T training is made difficult by the huge memory requirements, and complicated neural structure. A common solution to ease the RNN-T training is to employ connectionist temporal classification (CTC) model along with RNN language model (RNNLM) to initialize the RNN-T parameters. In this work, we conversely leverage external alignments to seed the RNN-T model. Two different pre-training solutions are explored, referred to as encoder pre-training, and whole-network pre-training respectively. Evaluated on Microsoft 65,000 hours anonymized production data with personally identifiable information removed, our proposed methods can obtain significant improvement. In particular, the encoder pre-training solution achieved a 10% and a 8% relative word error rate reduction when compared with random initialization and the widely used CTC+RNNLM initialization strategy, respectively. Our solutions also significantly reduce the RNN-T model latency from the baseline.

cs.CL↗

arXiv2020

Stacked Convolutional Deep Encoding Network for Video-Text Retrieval

Existing dominant approaches for cross-modal video-text retrieval task are to learn a joint embedding space to measure the cross-modal similarity. However, these methods rarely explore long-range dependency inside video frames or textual words leading to insufficient textual and visual details. In this paper, we propose a stacked convolutional deep encoding network for video-text retrieval task, which considers to simultaneously encode long-range and short-range dependency in the videos and texts. Specifically, a multi-scale dilated convolutional (MSDC) block within our approach is able to encode short-range temporal cues between video frames or text words by adopting different scales of kernel size and dilation size of convolutional layer. A stacked structure is designed to expand the receptive fields by repeatedly adopting the MSDC block, which further captures the long-range relations between these cues. Moreover, to obtain more robust textual representations, we fully utilize the powerful language model named Transformer in two stages: pretraining phrase and fine-tuning phrase. Extensive experiments on two different benchmark datasets (MSR-VTT, MSVD) show that our proposed method outperforms other state-of-the-art approaches.

cs.MM↗

arXiv2020

Learning to Cluster Faces via Confidence and Connectivity Estimation

Face clustering is an essential tool for exploiting the unlabeled face data, and has a wide range of applications including face annotation and retrieval. Recent works show that supervised clustering can result in noticeable performance gain. However, they usually involve heuristic steps and require numerous overlapped subgraphs, severely restricting their accuracy and efficiency. In this paper, we propose a fully learnable clustering framework without requiring a large number of overlapped subgraphs. Instead, we transform the clustering problem into two sub-problems. Specifically, two graph convolutional networks, named GCN-V and GCN-E, are designed to estimate the confidence of vertices and the connectivity of edges, respectively. With the vertex confidence and edge connectivity, we can naturally organize more relevant vertices on the affinity graph and group them into clusters. Experiments on two large-scale benchmarks show that our method significantly improves clustering accuracy and thus performance of the recognition models trained on top, yet it is an order of magnitude more efficient than existing supervised methods.

cs.CV↗

arXiv2020

Anisotropy-induced Extrinsic Chirality and Chiral Discrimination of Surface Plasmon Polaritons

We present the characteristics of a simple waveguiding structure constructed by anisotropic birefringent crystal-metal-chiral medium, anisotropic-metal-chiral in short, and reveal the chiral-dependent dispersion and propagation properties of the surface plasmon polaritons (SPPs). We demonstrate its remarkable discrimination ability to the magnitude and sign of both the real and imaginary part of the chirality parameter. The anisotropy plays a key role in such performance and shows tuneable ability in enantiomeric discrimination even when the chirality parameter is complex-valued. Most importantly, the physical origin of chiral discrimination stems from the extrinsic chirality of the system, which arises from the mutual orientation of the SPPs and the optical axis. Moreover, we also clarify the fundamental physics behind the chiral discriminating behaviour by associating the intrinsic quantum spin Hall effect (QSHE) of the SPPs with the electromagnetic field analysis. This structure does not rely on complicated fabrication but provides the opportunity of on-chip surface-sensitive biosensing. We anticipate that our work will stimulate intensive research to investigate the anisotropy-induced chiral sensing techniques in plasmonic platforms.

physics.optics↗

arXiv2020

High-Accuracy and Low-Latency Speech Recognition with Two-Head Contextual Layer Trajectory LSTM Model

While the community keeps promoting end-to-end models over conventional hybrid models, which usually are long short-term memory (LSTM) models trained with a cross entropy criterion followed by a sequence discriminative training criterion, we argue that such conventional hybrid models can still be significantly improved. In this paper, we detail our recent efforts to improve conventional hybrid LSTM acoustic models for high-accuracy and low-latency automatic speech recognition. To achieve high accuracy, we use a contextual layer trajectory LSTM (cltLSTM), which decouples the temporal modeling and target classification tasks, and incorporates future context frames to get more information for accurate acoustic modeling. We further improve the training strategy with sequence-level teacher-student learning. To obtain low latency, we design a two-head cltLSTM, in which one head has zero latency and the other head has a small latency, compared to an LSTM. When trained with Microsoft's 65 thousand hours of anonymized training data and evaluated with test sets with 1.8 million words, the proposed two-head cltLSTM model with the proposed training strategy yields a 28.2\% relative WER reduction over the conventional LSTM acoustic model, with a similar perceived latency.

eess.AS↗

arXiv2020

Harvest-and-Opportunistically-Relay: Analyses on Transmission Outage and Covertness

For enhancing transmission performance, privacy level and energy manipulating efficiency of wireless networks, this paper initiates a novel simultaneous wireless information and power transfer (SWIPT) full-duplex (FD) relaying protocol, termed harvest-and-opportunistically-relay (HOR). In the proposed HOR protocol, the relay can work opportunistically in either pure energy harvesting (PEH) or the FD SWIPT mode. Due to the FD characteristics, the dynamic fluctuation of R's residual energy is difficult to quantify and track. To solve this problem, we apply a novel discrete-state Markov Chain (MC) method in which the practical finite-capacity energy storage is considered. Furthermore, to improve the privacy level of the proposed HOR relaying system, covert transmission performance analysis is developed and investigated, where closed-form expressions of optimal detection threshold and minimum detection error probability are derived. Last but not least, with the aid of stationary distribution of the MC, closed-form expression of transmission outage probability is calculated, based on which transmission outage performance is analyzed. Numerical results have validated the correctness of analyses on transmission outage and covert communication. The impacts of key system parameters on the performance of transmission outage and covert communication are given and discussed. Based on mathematical analysis and numerical results, it is fair to say that the proposed HOR model is able to not only reliably enhance the transmission performance via smartly managing residual energy but also efficiently improve the privacy level of the legitimate transmission party via dynamically adjust the optimal detection threshold.

eess.SP↗