arXiv subjects

Bin Li

Publications and source records attributed to Bin Li.

At least 541 records · Page 30Linked to original sources

arXiv2021

DuCN: Dual-children Network for Medical Diagnosis and Similar Case Recommendation towards COVID-19

Early detection of the coronavirus disease 2019 (COVID-19) helps to treat patients timely and increase the cure rate, thus further suppressing the spread of the disease. In this study, we propose a novel deep learning based detection and similar case recommendation network to help control the epidemic. Our proposed network contains two stages: the first one is a lung region segmentation step and is used to exclude irrelevant factors, and the second is a detection and recommendation stage. Under this framework, in the second stage, we develop a dual-children network (DuCN) based on a pre-trained ResNet-18 to simultaneously realize the disease diagnosis and similar case recommendation. Besides, we employ triplet loss and intrapulmonary distance maps to assist the detection, which helps incorporate tiny differences between two images and is conducive to improving the diagnostic accuracy. For each confirmed COVID-19 case, we give similar cases to provide radiologists with diagnosis and treatment references. We conduct experiments on a large publicly available dataset (CC-CCII) and compare the proposed model with state-of-the-art COVID-19 detection methods. The results show that our proposed model achieves a promising clinical performance.

eess.IV↗

arXiv2021

BezierSeg: Parametric Shape Representation for Fast Object Segmentation in Medical Images

Delineating the lesion area is an important task in image-based diagnosis. Pixel-wise classification is a popular approach to segmenting the region of interest. However, at fuzzy boundaries such methods usually result in glitches, discontinuity, or disconnection, inconsistent with the fact that lesions are solid and smooth. To overcome these undesirable artifacts, we propose the BezierSeg model which outputs bezier curves encompassing the region of interest. Directly modelling the contour with analytic equations ensures that the segmentation is connected, continuous, and the boundary is smooth. In addition, it offers sub-pixel accuracy. Without loss of accuracy, the bezier contour can be resampled and overlaid with images of any resolution. Moreover, a doctor can conveniently adjust the curve's control points to refine the result. Our experiments show that the proposed method runs in real time and achieves accuracy competitive with pixel-wise segmentation models.

cs.CV↗

arXiv2021

Zero-Shot Chinese Character Recognition with Stroke-Level Decomposition

Chinese character recognition has attracted much research interest due to its wide applications. Although it has been studied for many years, some issues in this field have not been completely resolved yet, e.g. the zero-shot problem. Previous character-based and radical-based methods have not fundamentally addressed the zero-shot problem since some characters or radicals in test sets may not appear in training sets under a data-hungry condition. Inspired by the fact that humans can generalize to know how to write characters unseen before if they have learned stroke orders of some characters, we propose a stroke-based method by decomposing each character into a sequence of strokes, which are the most basic units of Chinese characters. However, we observe that there is a one-to-many relationship between stroke sequences and Chinese characters. To tackle this challenge, we employ a matching-based strategy to transform the predicted stroke sequence to a specific character. We evaluate the proposed method on handwritten characters, printed artistic characters, and scene characters. The experimental results validate that the proposed method outperforms existing methods on both character zero-shot and radical zero-shot tasks. Moreover, the proposed method can be easily generalized to other languages whose characters can be decomposed into strokes.

cs.CV↗

arXiv2021

Probing Magnetic Moment Operators in $H γ$ Production and $H \to τ^+ τ^- γ$ Rare Decay

The magnetic moment ($a_γ$) and weak magnetic moment ($a_W$) of charged leptons and quarks are sensitive to quantum effects of new physics heavy resonances. In effective field theory $a_γ$ and $a_W$ are induced by two independent operators, therefore, one has to measure both the $a_γ$ and $a_W$ to shed lights on new physics. The $a_W$'s of the SM fermions are measured at the LEP. In this work, we analyze the contributions from magnetic and weak magnetic moment operators in the processes of $pp\to H γ$ and $gg\to H \to τ^+ τ^- γ$ at the High-Luminosity Large Hadron Collider. We demonstrate that the two processes could cover most of the parameter space that cannot be probed at the LEP.

hep-ph↗

arXiv2021

Hashing-Accelerated Graph Neural Networks for Link Prediction

Networks are ubiquitous in the real world. Link prediction, as one of the key problems for network-structured data, aims to predict whether there exists a link between two nodes. The traditional approaches are based on the explicit similarity computation between the compact node representation by embedding each node into a low-dimensional space. In order to efficiently handle the intensive similarity computation in link prediction, the hashing technique has been successfully used to produce the node representation in the Hamming space. However, the hashing-based link prediction algorithms face accuracy loss from the randomized hashing techniques or inefficiency from the learning to hash techniques in the embedding process. Currently, the Graph Neural Network (GNN) framework has been widely applied to the graph-related tasks in an end-to-end manner, but it commonly requires substantial computational resources and memory costs due to massive parameter learning, which makes the GNN-based algorithms impractical without the help of a powerful workhorse. In this paper, we propose a simple and effective model called #GNN, which balances the trade-off between accuracy and efficiency. #GNN is able to efficiently acquire node representation in the Hamming space for link prediction by exploiting the randomized hashing technique to implement message passing and capture high-order proximity in the GNN framework. Furthermore, we characterize the discriminative power of #GNN in probability. The extensive experimental results demonstrate that the proposed #GNN algorithm achieves accuracy comparable to the learning-based algorithms and outperforms the randomized algorithm, while running significantly faster than the learning-based algorithms. Also, the proposed algorithm shows excellent scalability on a large-scale network with the limited resources.

cs.LG↗

arXiv2021

New Physics and Two Boosted W-jets plus Missing Energy

We show that the signature of two boosted $W$-jets plus large missing energy is very promising to probe heavy charged resonances ($X^\pm$) through the process of $pp\to X^+X^-\to W^+W^- X^0 X^0$ where $X^0$ denotes dark matter candidate. The hadronic decay mode of the $W$ boson is considered to maximize the number of signal events. When the mass split between $X^\pm$ and $X^0$ is large, one has to utilize the jet-substructure technique to analyze the boosted $W$-jet. For illustration we consider the process of chargino pair production at the LHC, i.e., $pp\to χ_1^+χ^-_1 \to W^+W^-χ_1^0χ_1^0$, and demonstrate that the proposed signature is able to cover more parameter space of $m_{χ_1^\pm}$ and $m_{χ_1^0}$ than the conventional signature of multiple leptons plus missing energy. More importantly, the signature of our interests is not sensitive to the spin of heavy resonances.

hep-ph↗

arXiv2021

POND: Pessimistic-Optimistic oNline Dispatching

This paper considers constrained online dispatching with unknown arrival, reward and constraint distributions. We propose a novel online dispatching algorithm, named POND, standing for Pessimistic-Optimistic oNline Dispatching, which achieves $O(\sqrt{T})$ regret and $O(1)$ constraint violation. Both bounds are sharp. Our experiments on synthetic and real datasets show that POND achieves low regret with minimal constraint violations.

cs.LG↗

arXiv2021

Context-Based Soft Actor Critic for Environments with Non-stationary Dynamics

The performance of deep reinforcement learning methods prone to degenerate when applied to environments with non-stationary dynamics. In this paper, we utilize the latent context recurrent encoders motivated by recent Meta-RL materials, and propose the Latent Context-based Soft Actor Critic (LC-SAC) method to address aforementioned issues. By minimizing the contrastive prediction loss function, the learned context variables capture the information of the environment dynamics and the recent behavior of the agent. Then combined with the soft policy iteration paradigm, the LC-SAC method alternates between soft policy evaluation and soft policy improvement until it converges to the optimal policy. Experimental results show that the performance of LC-SAC is significantly better than the SAC algorithm on the MetaWorld ML1 tasks whose dynamics changes drasticly among different episodes, and is comparable to SAC on the continuous control benchmark task MuJoCo whose dynamics changes slowly or doesn't change between different episodes. In addition, we also conduct relevant experiments to determine the impact of different hyperparameter settings on the performance of the LC-SAC algorithm and give the reasonable suggestions of hyperparameter setting.

cs.LG↗

arXiv2021

Improving Cost Learning for JPEG Steganography by Exploiting JPEG Domain Knowledge

Although significant progress in automatic learning of steganographic cost has been achieved recently, existing methods designed for spatial images are not well applicable to JPEG images which are more common media in daily life. The difficulties of migration mostly lie in the unique and complicated JPEG characteristics caused by 8x8 DCT mode structure. To address the issue, in this paper we extend an existing automatic cost learning scheme to JPEG, where the proposed scheme called JEC-RL (JPEG Embedding Cost with Reinforcement Learning) is explicitly designed to tailor the JPEG DCT structure. It works with the embedding action sampling mechanism under reinforcement learning, where a policy network learns the optimal embedding policies via maximizing the rewards provided by an environment network. The policy network is constructed following a domain-transition design paradigm, where three modules including pixel-level texture complexity evaluation, DCT feature extraction, and mode-wise rearrangement, are proposed. These modules operate in serial, gradually extracting useful features from a decompressed JPEG image and converting them into embedding policies for DCT elements, while considering JPEG characteristics including inter-block and intra-block correlations simultaneously. The environment network is designed in a gradient-oriented way to provide stable reward values by using a wide architecture equipped with a fixed preprocessing layer with 8x8 DCT basis filters. Extensive experiments and ablation studies demonstrate that the proposed method can achieve good security performance for JPEG images against both advanced feature based and modern CNN based steganalyzers.

cs.CR↗

arXiv2021

Decomposed Soft Actor-Critic Method for Cooperative Multi-Agent Reinforcement Learning

Deep reinforcement learning methods have shown great performance on many challenging cooperative multi-agent tasks. Two main promising research directions are multi-agent value function decomposition and multi-agent policy gradients. In this paper, we propose a new decomposed multi-agent soft actor-critic (mSAC) method, which effectively combines the advantages of the aforementioned two methods. The main modules include decomposed Q network architecture, discrete probabilistic policy and counterfactual advantage function (optinal). Theoretically, mSAC supports efficient off-policy learning and addresses credit assignment problem partially in both discrete and continuous action spaces. Tested on StarCraft II micromanagement cooperative multiagent benchmark, we empirically investigate the performance of mSAC against its variants and analyze the effects of the different components. Experimental results demonstrate that mSAC significantly outperforms policy-based approach COMA, and achieves competitive results with SOTA value-based approach Qmix on most tasks in terms of asymptotic perfomance metric. In addition, mSAC achieves pretty good results on large action space tasks, such as 2c_vs_64zg and MMM2.

cs.AI↗

arXiv2021

Performance of CRC Concatenated Pre-transformed RM-Polar Codes

In this paper, we discuss pre-transformed RM-Polar codes and cyclic redundancy check (CRC) concatenated pre-transformed RM-Polar codes. The simulation results show that the pre-transformed RM-Polar (256, 128+9) code concatenated with 9-bit CRC can achieve a frame error rate (FER) of 0.001 at Eb/No=1.95dB under the list decoding, which is about 0.05dB from the RCU bound. The pre-transformed RM-Polar (512, 256+9) concatenated with 9-bit CRC can achieve a FER of 0.001 at Eb/No=1.6dB under the list decoding, which is 0.15dB from the RCU bound.

cs.IT↗

arXiv2021

East Asian VLBI Network Observations of Active Galactic Nuclei Jets: Imaging with KaVA+Tianma+Nanshan

The East Asian very-long-baseline interferometry (VLBI) Network (EAVN) is a rapidly evolving international VLBI array that is currently promoted under joint efforts among China, Japan, and Korea. EAVN aims at forming a joint VLBI Network by combining a large number of radio telescopes distributed over East Asian regions. After the combination of the Korean VLBI Network (KVN) and the VLBI Exploration of Radio Astrometry (VERA) into KaVA, further expansion with the joint array in East Asia is actively promoted. Here we report the first imaging results (at 22 and 43 GHz) of bright radio sources obtained with KaVA connected to Tianma 65-m and Nanshan 26-m Radio Telescopes in China. To test the EAVN imaging performance for different sources, we observed four active galactic nuclei (AGN) having different brightness and morphology. As a result, we confirmed that Tianma 65-m Radio Telescope (TMRT) significantly enhances the overall array sensitivity, a factor of 4 improvement in baseline sensitivity and 2 in image dynamic range compared to the case of KaVA only. The addition of Nanshan 26-m Radio Telescope (NSRT) further doubled the east-west angular resolution. With the resulting high-dynamic-range, high-resolution images with EAVN (KaVA+TMRT+NSRT), various fine-scale structures in our targets, such as the counter-jet in M87, a kink-like morphology of the 3C273 jet and the weak emission in other sources, are successfully detected. This demonstrates the powerful capability of EAVN to study AGN jets and to achieve other science goals in general. Ongoing expansion of EAVN will further enhance the angular resolution, detection sensitivity and frequency coverage of the network.

astro-ph.GA↗

arXiv2021

Sparse online relative similarity learning

For many data mining and machine learning tasks, the quality of a similarity measure is the key for their performance. To automatically find a good similarity measure from datasets, metric learning and similarity learning are proposed and studied extensively. Metric learning will learn a Mahalanobis distance based on positive semi-definite (PSD) matrix, to measure the distances between objectives, while similarity learning aims to directly learn a similarity function without PSD constraint so that it is more attractive. Most of the existing similarity learning algorithms are online similarity learning method, since online learning is more scalable than offline learning. However, most existing online similarity learning algorithms learn a full matrix with d 2 parameters, where d is the dimension of the instances. This is clearly inefficient for high dimensional tasks due to its high memory and computational complexity. To solve this issue, we introduce several Sparse Online Relative Similarity (SORS) learning algorithms, which learn a sparse model during the learning process, so that the memory and computational cost can be significantly reduced. We theoretically analyze the proposed algorithms, and evaluate them on some real-world high dimensional datasets. Encouraging empirical results demonstrate the advantages of our approach in terms of efficiency and efficacy.

cs.LG↗

arXiv2021

Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learning

We address the challenging problem of whole slide image (WSI) classification. WSIs have very high resolutions and usually lack localized annotations. WSI classification can be cast as a multiple instance learning (MIL) problem when only slide-level labels are available. We propose a MIL-based method for WSI classification and tumor detection that does not require localized annotations. Our method has three major components. First, we introduce a novel MIL aggregator that models the relations of the instances in a dual-stream architecture with trainable distance measurement. Second, since WSIs can produce large or unbalanced bags that hinder the training of MIL models, we propose to use self-supervised contrastive learning to extract good representations for MIL and alleviate the issue of prohibitive memory cost for large bags. Third, we adopt a pyramidal fusion mechanism for multiscale WSI features, and further improve the accuracy of classification and localization. Our model is evaluated on two representative WSI datasets. The classification accuracy of our model compares favorably to fully-supervised methods, with less than 2% accuracy gap across datasets. Our results also outperform all previous MIL-based methods. Additional benchmark results on standard MIL datasets further demonstrate the superior performance of our MIL aggregator on general MIL problems. GitHub repository: https://github.com/binli123/dsmil-wsi

cs.CV↗

arXiv2021

Anisotropic transport and de Haas$-$van Alphen oscillations in quasi-one-dimensional TaPtTe$_5$

Because of the unique physical properties and potential applications, the exploration of quantum materials with diverse symmetry-protected topological states has attracted considerable interest in the condensed-matter community in recent years. Most of the topologically nontirvial materials identified thus far have two-dimensional or three-dimensional structural characteristics, while the quasi-one-dimensional (quasi-1D) analogs are rare. Here we report on anisotropic magnetoresistance, Hall effect, and quantum de Haas$-$van Alphen (dHvA) oscillations in TaPtTe$_5$ single crystals, which possess a layered crystal structure with quasi-1D PtTe$_2$ chains. TaPtTe$_5$ manifests an anisotropic magnetoresistance and a nonlinear Hall effect at low temperatures. The analysis of the dHvA oscillations reveals two major oscillation frequencies (63.5 T and 95.2 T). The corresponding light effective masses and the nonzero Berry phases suggest the nontrivial band topology in TaPtTe$_5$, which is further corroborated by the first-principles calculations. Our results suggest that TaPtTe$_5$, in analogy with its sister compounds TaPdTe$_5$ and TaNiTe$_5$, is another quasi-1D material hosting topological Dirac fermions.

cond-mat.str-el↗

arXiv2021

Knowledge-Guided Object Discovery with Acquired Deep Impressions

We present a framework called Acquired Deep Impressions (ADI) which continuously learns knowledge of objects as "impressions" for compositional scene understanding. In this framework, the model first acquires knowledge from scene images containing a single object in a supervised manner, and then continues to learn from novel multi-object scene images which may contain objects that have not been seen before without any further supervision, under the guidance of the learned knowledge as humans do. By memorizing impressions of objects into parameters of neural networks and applying the generative replay strategy, the learned knowledge can be reused to generate images with pseudo-annotations and in turn assist the learning of novel scenes. The proposed ADI framework focuses on the acquisition and utilization of knowledge, and is complementary to existing deep generative models proposed for compositional scene representation. We adapt a base model to make it fall within the ADI framework and conduct experiments on two types of datasets. Empirical results suggest that the proposed framework is able to effectively utilize the acquired impressions and improve the scene decomposition performance.

cs.LG↗

arXiv2021

Deformable DETR: Deformable Transformers for End-to-End Object Detection

DETR has been recently proposed to eliminate the need for many hand-designed components in object detection while demonstrating good performance. However, it suffers from slow convergence and limited feature spatial resolution, due to the limitation of Transformer attention modules in processing image feature maps. To mitigate these issues, we proposed Deformable DETR, whose attention modules only attend to a small set of key sampling points around a reference. Deformable DETR can achieve better performance than DETR (especially on small objects) with 10 times less training epochs. Extensive experiments on the COCO benchmark demonstrate the effectiveness of our approach. Code is released at https://github.com/fundamentalvision/Deformable-DETR.

cs.CV↗

arXiv2021

PENet: Towards Precise and Efficient Image Guided Depth Completion

Image guided depth completion is the task of generating a dense depth map from a sparse depth map and a high quality image. In this task, how to fuse the color and depth modalities plays an important role in achieving good performance. This paper proposes a two-branch backbone that consists of a color-dominant branch and a depth-dominant branch to exploit and fuse two modalities thoroughly. More specifically, one branch inputs a color image and a sparse depth map to predict a dense depth map. The other branch takes as inputs the sparse depth map and the previously predicted depth map, and outputs a dense depth map as well. The depth maps predicted from two branches are complimentary to each other and therefore they are adaptively fused. In addition, we also propose a simple geometric convolutional layer to encode 3D geometric cues. The geometric encoded backbone conducts the fusion of different modalities at multiple stages, leading to good depth completion results. We further implement a dilated and accelerated CSPN++ to refine the fused depth map efficiently. The proposed full model ranks 1st in the KITTI depth completion online leaderboard at the time of submission. It also infers much faster than most of the top ranked methods. The code of this work is available at https://github.com/JUGGHM/PENet_ICRA2021.

cs.CV↗