arXiv subjects

Jun Wang

Publications and source records attributed to Jun Wang.

At least 1,009 records · Page 56Linked to original sources

arXiv2020

Semi-Siamese Training for Shallow Face Learning

Most existing public face datasets, such as MS-Celeb-1M and VGGFace2, provide abundant information in both breadth (large number of IDs) and depth (sufficient number of samples) for training. However, in many real-world scenarios of face recognition, the training dataset is limited in depth, i.e. only two face images are available for each ID. $\textit{We define this situation as Shallow Face Learning, and find it problematic with existing training methods.}$ Unlike deep face data, the shallow face data lacks intra-class diversity. As such, it can lead to collapse of feature dimension and consequently the learned network can easily suffer from degeneration and over-fitting in the collapsed dimension. In this paper, we aim to address the problem by introducing a novel training method named Semi-Siamese Training (SST). A pair of Semi-Siamese networks constitute the forward propagation structure, and the training loss is computed with an updating gallery queue, conducting effective optimization on shallow training data. Our method is developed without extra-dependency, thus can be flexibly integrated with the existing loss functions and network architectures. Extensive experiments on various benchmarks of face recognition show the proposed method significantly improves the training, not only in shallow face learning, but also for conventional deep face data.

cs.CV↗

arXiv2020

InfoFocus: 3D Object Detection for Autonomous Driving with Dynamic Information Modeling

Real-time 3D object detection is crucial for autonomous cars. Achieving promising performance with high efficiency, voxel-based approaches have received considerable attention. However, previous methods model the input space with features extracted from equally divided sub-regions without considering that point cloud is generally non-uniformly distributed over the space. To address this issue, we propose a novel 3D object detection framework with dynamic information modeling. The proposed framework is designed in a coarse-to-fine manner. Coarse predictions are generated in the first stage via a voxel-based region proposal network. We introduce InfoFocus, which improves the coarse detections by adaptively refining features guided by the information of point cloud density. Experiments are conducted on the large-scale nuScenes 3D detection benchmark. Results show that our framework achieves the state-of-the-art performance with 31 FPS and improves our baseline significantly by 9.0% mAP on the nuScenes test set.

cs.CV↗

arXiv2020

Actor-Critic Reinforcement Learning for Control with Stability Guarantee

Reinforcement Learning (RL) and its integration with deep learning have achieved impressive performance in various robotic control tasks, ranging from motion planning and navigation to end-to-end visual manipulation. However, stability is not guaranteed in model-free RL by solely using data. From a control-theoretic perspective, stability is the most important property for any control system, since it is closely related to safety, robustness, and reliability of robotic systems. In this paper, we propose an actor-critic RL framework for control which can guarantee closed-loop stability by employing the classic Lyapunov's method in control theory. First of all, a data-based stability theorem is proposed for stochastic nonlinear systems modeled by Markov decision process. Then we show that the stability condition could be exploited as the critic in the actor-critic RL to learn a controller/policy. At last, the effectiveness of our approach is evaluated on several well-known 3-dimensional robot control tasks and a synthetic biology gene network tracking task in three different popular physics simulation platforms. As an empirical evaluation on the advantage of stability, we show that the learned policies can enable the systems to recover to the equilibrium or way-points when interfered by uncertainties such as system parametric variations and external disturbances to a certain extent.

cs.RO↗

arXiv2020

Bidirectional Loss Function for Label Enhancement and Distribution Learning

Label distribution learning (LDL) is an interpretable and general learning paradigm that has been applied in many real-world applications. In contrast to the simple logical vector in single-label learning (SLL) and multi-label learning (MLL), LDL assigns labels with a description degree to each instance. In practice, two challenges exist in LDL, namely, how to address the dimensional gap problem during the learning process of LDL and how to exactly recover label distributions from existing logical labels, i.e., Label Enhancement (LE). For most existing LDL and LE algorithms, the fact that the dimension of the input matrix is much higher than that of the output one is alway ignored and it typically leads to the dimensional reduction owing to the unidirectional projection. The valuable information hidden in the feature space is lost during the mapping process. To this end, this study considers bidirectional projections function which can be applied in LE and LDL problems simultaneously. More specifically, this novel loss function not only considers the mapping errors generated from the projection of the input space into the output one but also accounts for the reconstruction errors generated from the projection of the output space back to the input one. This loss function aims to potentially reconstruct the input data from the output data. Therefore, it is expected to obtain more accurate results. Finally, experiments on several real-world datasets are carried out to demonstrate the superiority of the proposed method for both LE and LDL.

cs.LG↗

arXiv2020

A Soft Cancellation Decoder for Parity-Check Polar Codes

Polar codes has been selected as the channel coding scheme for 5G new radio (NR) control channel. Specifically, a special type of parity-check polar (PC-Polar) codes was adopted in uplink control information (UCI). In this paper, we propose a parity-check soft-cancellation (PC-SCAN) algorithm and its simplified version to decode PC-Polar codes. The potential benefits are two-fold. First, PC-SCAN can provide soft output for PC-Polar codes, which is essential for advanced turbo receivers. Second, the decoding performance is better than that of successive cancellation (SC). This is due to the fact that parity-check constraints can be exploited by PC-SCAN to enhance the reliability of other information bits over the iterations. Moreover, we describe a cyclic-shift-register (CSR) based implementation "CSR-SCAN" to reduce both hardware cost and latency with minimum performance loss.

cs.IT↗

arXiv2020

Structural Landmarking and Interaction Modelling: on Resolution Dilemmas in Graph Classification

Graph neural networks are promising architecture for learning and inference with graph-structured data. Yet difficulties in modelling the ``parts'' and their ``interactions'' still persist in terms of graph classification, where graph-level representations are usually obtained by squeezing the whole graph into a single vector through graph pooling. From complex systems point of view, mixing all the parts of a system together can affect both model interpretability and predictive performance, because properties of a complex system arise largely from the interaction among its components. We analyze the intrinsic difficulty in graph classification under the unified concept of ``resolution dilemmas'' with learning theoretic recovery guarantees, and propose ``SLIM'', an inductive neural network model for Structural Landmarking and Interaction Modelling. It turns out, that by solving the resolution dilemmas, and leveraging explicit interacting relation between component parts of a graph to explain its complexity, SLIM is more interpretable, accurate, and offers new insight in graph representation learning.

cs.LG↗

arXiv2020

Resisting Crowd Occlusion and Hard Negatives for Pedestrian Detection in the Wild

Pedestrian detection has been heavily studied in the last decade due to its wide application. Despite incremental progress, crowd occlusion and hard negatives are still challenging current state-of-the-art pedestrian detectors. In this paper, we offer two approaches based on the general region-based detection framework to tackle these challenges. Specifically, to address the occlusion, we design a novel coulomb loss as a regulator on bounding box regression, in which proposals are attracted by their target instance and repelled by the adjacent non-target instances. For hard negatives, we propose an efficient semantic-driven strategy for selecting anchor locations, which can sample informative negative examples at training phase for classification refinement. It is worth noting that these methods can also be applied to general object detection domain, and trainable in an end-to-end manner. We achieves consistently high performance on the Caltech-USA and CityPersons benchmarks.

cs.CV↗

arXiv2020

ControlVAE: Controllable Variational Autoencoder

Variational Autoencoders (VAE) and their variants have been widely used in a variety of applications, such as dialog generation, image generation and disentangled representation learning. However, the existing VAE models have some limitations in different applications. For example, a VAE easily suffers from KL vanishing in language modeling and low reconstruction quality for disentangling. To address these issues, we propose a novel controllable variational autoencoder framework, ControlVAE, that combines a controller, inspired by automatic control theory, with the basic VAE to improve the performance of resulting generative models. Specifically, we design a new non-linear PI controller, a variant of the proportional-integral-derivative (PID) control, to automatically tune the hyperparameter (weight) added in the VAE objective using the output KL-divergence as feedback during model training. The framework is evaluated using three applications; namely, language modeling, disentangled representation learning, and image generation. The results show that ControlVAE can achieve better disentangling and reconstruction quality than the existing methods. For language modelling, it not only averts the KL-vanishing, but also improves the diversity of generated text. Finally, we also demonstrate that ControlVAE improves the reconstruction quality of generated images compared to the original VAE.

cs.LG↗

arXiv2020

Automated Radiological Report Generation For Chest X-Rays With Weakly-Supervised End-to-End Deep Learning

The chest X-Ray (CXR) is the one of the most common clinical exam used to diagnose thoracic diseases and abnormalities. The volume of CXR scans generated daily in hospitals is huge. Therefore, an automated diagnosis system able to save the effort of doctors is of great value. At present, the applications of artificial intelligence in CXR diagnosis usually use pattern recognition to classify the scans. However, such methods rely on labeled databases, which are costly and usually have large error rates. In this work, we built a database containing more than 12,000 CXR scans and radiological reports, and developed a model based on deep convolutional neural network and recurrent network with attention mechanism. The model learns features from the CXR scans and the associated raw radiological reports directly; no additional labeling of the scans are needed. The model provides automated recognition of given scans and generation of reports. The quality of the generated reports was evaluated with both the CIDEr scores and by radiologists as well. The CIDEr scores are found to be around 5.8 on average for the testing dataset. Further blind evaluation suggested a comparable performance against human radiologist.

cs.CV↗

arXiv2020

Hyperspectral Super-Resolution via Interpretable Block-Term Tensor Modeling

This work revisits coupled tensor decomposition (CTD)-based hyperspectral super-resolution (HSR). HSR aims at fusing a pair of hyperspectral and multispectral images to recover a super-resolution image (SRI). The vast majority of the HSR approaches take a low-rank matrix recovery perspective. The challenge is that theoretical guarantees for recovering the SRI using low-rank matrix models are either elusive or derived under stringent conditions. A couple of recent CTD-based methods ensure recoverability for the SRI under relatively mild conditions, leveraging on algebraic properties of the canonical polyadic decomposition (CPD) and the Tucker decomposition models, respectively. However, the latent factors of both the CPD and Tucker models have no physical interpretations in the context of spectral image analysis, which makes incorporating prior information challenging---but using priors is often essential for enhancing performance in noisy environments. This work employs an idea that models spectral images as tensors following the block-term decomposition model with multilinear rank-$(L_r, L_r, 1)$ terms (i.e., the LL1 model) and formulates the HSR problem as a coupled LL1 tensor decomposition problem. Similar to the existing CTD approaches, recoverability of the SRI is shown under mild conditions. More importantly, the latent factors of the LL1 model can be interpreted as the key constituents of spectral images, i.e., the endmembers' spectral signatures and abundance maps. This connection allows us to easily incorporate prior information for performance enhancement. A flexible algorithmic framework that can work with a series of structural information is proposed to take advantage of the model interpretability. The effectiveness is showcased using simulated and real data.

eess.SP↗

arXiv2020

SAMBA: Safe Model-Based & Active Reinforcement Learning

In this paper, we propose SAMBA, a novel framework for safe reinforcement learning that combines aspects from probabilistic modelling, information theory, and statistics. Our method builds upon PILCO to enable active exploration using novel(semi-)metrics for out-of-sample Gaussian process evaluation optimised through a multi-objective problem that supports conditional-value-at-risk constraints. We evaluate our algorithm on a variety of safe dynamical system benchmarks involving both low and high-dimensional state representations. Our results show orders of magnitude reductions in samples and violations compared to state-of-the-art methods. Lastly, we provide intuition as to the effectiveness of the framework by a detailed analysis of our active metrics and safety constraints.

cs.LG↗

arXiv2020

Multi-Agent Interactions Modeling with Correlated Policies

In multi-agent systems, complex interacting behaviors arise due to the high correlations among agents. However, previous work on modeling multi-agent interactions from demonstrations is primarily constrained by assuming the independence among policies and their reward structures. In this paper, we cast the multi-agent interactions modeling problem into a multi-agent imitation learning framework with explicit modeling of correlated policies by approximating opponents' policies, which can recover agents' policies that can regenerate similar interactions. Consequently, we develop a Decentralized Adversarial Imitation Learning algorithm with Correlated policies (CoDAIL), which allows for decentralized training and execution. Various experiments demonstrate that CoDAIL can better regenerate complex interactions close to the demonstrators and outperforms state-of-the-art multi-agent imitation learning methods. Our code is available at \url{https://github.com/apexrl/CoDAIL}.

cs.MA↗

arXiv2020

Multi-Agent Determinantal Q-Learning

Centralized training with decentralized execution has become an important paradigm in multi-agent learning. Though practical, current methods rely on restrictive assumptions to decompose the centralized value function across agents for execution. In this paper, we eliminate this restriction by proposing multi-agent determinantal Q-learning. Our method is established on Q-DPP, an extension of determinantal point process (DPP) with partition-matroid constraint to multi-agent setting. Q-DPP promotes agents to acquire diverse behavioral models; this allows a natural factorization of the joint Q-functions with no need for \emph{a priori} structural constraints on the value function or special network architectures. We demonstrate that Q-DPP generalizes major solutions including VDN, QMIX, and QTRAN on decentralizable cooperative tasks. To efficiently draw samples from Q-DPP, we adopt an existing sample-by-projection sampler with theoretical approximation guarantee. The sampler also benefits exploration by coordinating agents to cover orthogonal directions in the state space during multi-agent training. We evaluate our algorithm on various cooperative benchmarks; its effectiveness has been demonstrated when compared with the state-of-the-art.

cs.LG↗

arXiv2020

Learning to Model Opponent Learning

Multi-Agent Reinforcement Learning (MARL) considers settings in which a set of coexisting agents interact with one another and their environment. The adaptation and learning of other agents induces non-stationarity in the environment dynamics. This poses a great challenge for value function-based algorithms whose convergence usually relies on the assumption of a stationary environment. Policy search algorithms also struggle in multi-agent settings as the partial observability resulting from an opponent's actions not being known introduces high variance to policy training. Modelling an agent's opponent(s) is often pursued as a means of resolving the issues arising from the coexistence of learning opponents. An opponent model provides an agent with some ability to reason about other agents to aid its own decision making. Most prior works learn an opponent model by assuming the opponent is employing a stationary policy or switching between a set of stationary policies. Such an approach can reduce the variance of training signals for policy search algorithms. However, in the multi-agent setting, agents have an incentive to continually adapt and learn. This means that the assumptions concerning opponent stationarity are unrealistic. In this work, we develop a novel approach to modelling an opponent's learning dynamics which we term Learning to Model Opponent Learning (LeMOL). We show our structured opponent model is more accurate and stable than naive behaviour cloning baselines. We further show that opponent modelling can improve the performance of algorithmic agents in multi-agent settings.

cs.LG↗

arXiv2020

A Deep Recurrent Survival Model for Unbiased Ranking

Position bias is a critical problem in information retrieval when dealing with implicit yet biased user feedback data. Unbiased ranking methods typically rely on causality models and debias the user feedback through inverse propensity weighting. While practical, these methods still suffer from two major problems. First, when inferring a user click, the impact of the contextual information, such as documents that have been examined, is often ignored. Second, only the position bias is considered but other issues resulted from user browsing behaviors are overlooked. In this paper, we propose an end-to-end Deep Recurrent Survival Ranking (DRSR), a unified framework to jointly model user's various behaviors, to (i) consider the rich contextual information in the ranking list; and (ii) address the hidden issues underlying user behaviors, i.e., to mine observe pattern in queries without any click (non-click queries), and to model tracking logs which cannot truly reflect the user browsing intents (untrusted observation). Specifically, we adopt a recurrent neural network to model the contextual information and estimates the conditional likelihood of user feedback at each position. We then incorporate survival analysis techniques with the probability chain rule to mathematically recover the unbiased joint probability of one user's various behaviors. DRSR can be easily incorporated with both point-wise and pair-wise learning objectives. The extensive experiments over two large-scale industrial datasets demonstrate the significant performance gains of our model comparing with the state-of-the-arts.

cs.IR↗

arXiv2020

Doubly resonant second-harmonic generation of a vortex beam from a bound state in the continuum

Second harmonic generation in nonlinear materials can be greatly enhanced by realizing doubly-resonant cavities with high quality factors. However, fulfilling such doubly resonant condition in photonic crystal (PhC) cavities is a long-standing challenge, because of the difficulty in engineering photonic bandgaps around both frequencies. Here, by implementing a second-harmonic bound state in the continuum (BIC) and confining it with a heterostructure design, we show the first doubly-resonant PhC slab cavity with $2.4\times10^{-2}$ W$^{-1}$ conversion efficiency under continuous wave excitation. We also report the confirmation of highly normal-direction concentrated far-field emission pattern with radial polarization at the second harmonic frequency. These results represent a solid verification of previous theoretical predictions and a cornerstone achievement, not only for nonlinear frequency conversion but also for vortex beam generation and prospective nonclassical sources of radiation.

physics.optics↗

arXiv2020

Learning from a Lightweight Teacher for Efficient Knowledge Distillation

Knowledge Distillation (KD) is an effective framework for compressing deep learning models, realized by a student-teacher paradigm requiring small student networks to mimic the soft target generated by well-trained teachers. However, the teachers are commonly assumed to be complex and need to be trained on the same datasets as students. This leads to a time-consuming training process. The recent study shows vanilla KD plays a similar role as label smoothing and develops teacher-free KD, being efficient and mitigating the issue of learning from heavy teachers. But because teacher-free KD relies on manually-crafted output distributions kept the same for all data instances belonging to the same class, its flexibility and performance are relatively limited. To address the above issues, this paper proposes en efficient knowledge distillation learning framework LW-KD, short for lightweight knowledge distillation. It firstly trains a lightweight teacher network on a synthesized simple dataset, with an adjustable class number equal to that of a target dataset. The teacher then generates soft target whereby an enhanced KD loss could guide student learning, which is a combination of KD loss and adversarial loss for making student output indistinguishable from the output of the teacher. Experiments on several public datasets with different modalities demonstrate LWKD is effective and efficient, showing the rationality of its main design principles.

cs.CV↗

arXiv2020

An Improved Method for the Fitting and Prediction of the Number of COVID-19 Confirmed Cases Based on LSTM

New coronavirus disease (COVID-19) has constituted a global pandemic and has spread to most countries and regions in the world. By understanding the development trend of a regional epidemic, the epidemic can be controlled using the development policy. The common traditional mathematical differential equations and population prediction models have limitations for time series population prediction, and even have large estimation errors. To address this issue, we propose an improved method for predicting confirmed cases based on LSTM (Long-Short Term Memory) neural network. This work compared the deviation between the experimental results of the improved LSTM prediction model and the digital prediction models (such as Logistic and Hill equations) with the real data as reference. And this work uses the goodness of fitting to evaluate the fitting effect of the improvement. Experiments show that the proposed approach has a smaller prediction deviation and a better fitting effect. Compared with the previous forecasting methods, the contributions of our proposed improvement methods are mainly in the following aspects: 1) we have fully considered the spatiotemporal characteristics of the data, rather than single standardized data; 2) the improved parameter settings and evaluation indicators are more accurate for fitting and forecasting. 3) we consider the impact of the epidemic stage and conduct reasonable data processing for different stage.

physics.soc-ph↗