arXiv subjects

Bin Li

Publications and source records attributed to Bin Li.

At least 505 records · Page 28Linked to original sources

arXiv2022

Towards Better Chinese-centric Neural Machine Translation for Low-resource Languages

The last decade has witnessed enormous improvements in science and technology, stimulating the growing demand for economic and cultural exchanges in various countries. Building a neural machine translation (NMT) system has become an urgent trend, especially in the low-resource setting. However, recent work tends to study NMT systems for low-resource languages centered on English, while few works focus on low-resource NMT systems centered on other languages such as Chinese. To achieve this, the low-resource multilingual translation challenge of the 2021 iFLYTEK AI Developer Competition provides the Chinese-centric multilingual low-resource NMT tasks, where participants are required to build NMT systems based on the provided low-resource samples. In this paper, we present the winner competition system that leverages monolingual word embeddings data enhancement, bilingual curriculum learning, and contrastive re-ranking. In addition, a new Incomplete-Trust (In-trust) loss function is proposed to replace the traditional cross-entropy loss when training. The experimental results demonstrate that the implementation of these ideas leads better performance than other state-of-the-art methods. All the experimental codes are released at: https://github.com/WENGSYX/Low-resource-text-translation.

cs.CL↗

arXiv2022

3D Perception based Imitation Learning under Limited Demonstration for Laparoscope Control in Robotic Surgery

Automatic laparoscope motion control is fundamentally important for surgeons to efficiently perform operations. However, its traditional control methods based on tool tracking without considering information hidden in surgical scenes are not intelligent enough, while the latest supervised imitation learning (IL)-based methods require expensive sensor data and suffer from distribution mismatch issues caused by limited demonstrations. In this paper, we propose a novel Imitation Learning framework for Laparoscope Control (ILLC) with reinforcement learning (RL), which can efficiently learn the control policy from limited surgical video clips. Specially, we first extract surgical laparoscope trajectories from unlabeled videos as the demonstrations and reconstruct the corresponding surgical scenes. To fully learn from limited motion trajectory demonstrations, we propose Shape Preserving Trajectory Augmentation (SPTA) to augment these data, and build a simulation environment that supports parallel RGB-D rendering to reinforce the RL policy for interacting with the environment efficiently. With adversarial training for IL, we obtain the laparoscope control policy based on the generated rollouts and surgical demonstrations. Extensive experiments are conducted in unseen reconstructed surgical scenes, and our method outperforms the previous IL methods, which proves the feasibility of our unified learning-based framework for laparoscope control.

cs.RO↗

arXiv2022

Towards Visual-Prompt Temporal Answering Grounding in Medical Instructional Video

The temporal answering grounding in the video (TAGV) is a new task naturally derived from temporal sentence grounding in the video (TSGV). Given an untrimmed video and a text question, this task aims at locating the matching span from the video that can semantically answer the question. Existing methods tend to formulate the TAGV task with a visual span-based question answering (QA) approach by matching the visual frame span queried by the text question. However, due to the weak correlations and huge gaps of the semantic features between the textual question and visual answer, existing methods adopting visual span predictor perform poorly in the TAGV task. To bridge these gaps, we propose a visual-prompt text span localizing (VPTSL) method, which introduces the timestamped subtitles as a passage to perform the text span localization for the input text question, and prompts the visual highlight features into the pre-trained language model (PLM) for enhancing the joint semantic representations. Specifically, the context query attention is utilized to perform cross-modal interaction between the extracted textual and visual features. Then, the highlight features are obtained through the video-text highlighting for the visual prompt. To alleviate semantic differences between textual and visual features, we design the text span predictor by encoding the question, the subtitles, and the prompted visual highlight features with the PLM. As a result, the TAGV task is formulated to predict the span of subtitles matching the visual answer. Extensive experiments on the medical instructional dataset, namely MedVidQA, show that the proposed VPTSL outperforms the state-of-the-art (SOTA) method by 28.36% in terms of mIOU with a large margin, which demonstrates the effectiveness of the proposed visual prompt and the text span predictor.

cs.CV↗

arXiv2022

Neural Compression-Based Feature Learning for Video Restoration

How to efficiently utilize the temporal features is crucial, yet challenging, for video restoration. The temporal features usually contain various noisy and uncorrelated information, and they may interfere with the restoration of the current frame. This paper proposes learning noise-robust feature representations to help video restoration. We are inspired by that the neural codec is a natural denoiser. In neural codec, the noisy and uncorrelated contents which are hard to predict but cost lots of bits are more inclined to be discarded for bitrate saving. Therefore, we design a neural compression module to filter the noise and keep the most useful information in features for video restoration. To achieve robustness to noise, our compression module adopts a spatial channel-wise quantization mechanism to adaptively determine the quantization step size for each position in the latent. Experiments show that our method can significantly boost the performance on video denoising, where we obtain 0.13 dB improvement over BasicVSR++ with only 0.23x FLOPs. Meanwhile, our method also obtains SOTA results on video deraining and dehazing.

cs.CV↗

arXiv2022

New Massive Contact Twin Binary in a Radio-quiet HII Region Associated with the M17 Complex

Early-B stars may create an HII region that appears as radio-quiet. We report the identification of new early-B stars associated with the radio-quiet HII region G014.645--00.606 in the M17 complex. The ratio-quiet HII region G014.645--00.606 is adjacent to three radio-quiet WISE HII region candidates. The ionizing sources of the radio-quiet HII regions are expected to later than B1V, given the sensitivity about 1-2 mJy of the MAGPIS 20 cm survey. The stars were first selected if their parallaxes of GAIA EDR3 match that of the 22 GHz H$_2$O maser source within the same region. We used the color-magnitude diagram made from the ZTF photometric catalog to select the candidates for massive stars because the intrinsic $g-r$ colors of massive stars change little from B-type to O-type stars. Five stars lie in the areas of the color-magnitude diagram where either reddened massive stars or evolved post-main sequence stars of lower masses are commonly found. Three of the five stars, sources 1, 2, and 3, are located at the cavities of the three IR bubbles, and extended H$α$ emission is detected around the three IR bubbles. We suggest that sources 1, 2, and 3 are candidates for early-B stars associated with the radio-quiet region G014.645--00.606. Particularly, source 1 is an EW type eclipsing binary with a short period of 0.825 day, while source 2 is an EA type eclipsing binary with a short period of 0.919 day. The physical parameters of the two binary systems have been derived through the PHOEBE model. Source 1 is a twin binary of two stars with T~23,500 K, and source 2 contains a hotter component (T~20,100 K) and a cooler one (T~15,500 K). The $O-C$ values of source 1 show a trend of decline, implying that the period of the source is deceasing. Source 1 is likely a contacting early-B twin binary, for which mass transfer might cause its orbit to shrink.

astro-ph.SR↗

arXiv2022

Multi-Unit Diffusion Auctions with Intermediaries

This paper studies multi-unit auctions powered by intermediaries, where each intermediary owns a private set of unit-demand buyers and all intermediaries are networked with each other. Our goal is to incentivize the intermediaries to diffuse the auction information to individuals they can reach, including their private buyers and neighboring intermediaries, so that more potential buyers are able to participate in the auction. To this end, we build a diffusion-based auction framework which incorporates the strategic interaction of intermediaries. It is showed that the classic Vickrey-Clarke-Groves (VCG) mechanism within the framework can achieve the maximum social welfare, but it may decrease the seller's revenue or even lead to a deficit. To overcome the revenue issue, we propose a novel auction, called critical neighborhood auction, which not only maximizes the social welfare, but also improves the seller's revenue comparing to the VCG mechanism with/without intermediaries.

cs.GT↗

arXiv2022

Enhancing Backdoor Attacks with Multi-Level MMD Regularization

While Deep Neural Networks (DNNs) excel in many tasks, the huge training resources they require become an obstacle for practitioners to develop their own models. It has become common to collect data from the Internet or hire a third party to train models. Unfortunately, recent studies have shown that these operations provide a viable pathway for maliciously injecting hidden backdoors into DNNs. Several defense methods have been developed to detect malicious samples, with the common assumption that the latent representations of benign and malicious samples extracted by the infected model exhibit different distributions. However, a comprehensive study on the distributional differences is missing. In this paper, we investigate such differences thoroughly via answering three questions: 1) What are the characteristics of the distributional differences? 2) How can they be effectively reduced? 3) What impact does this reduction have on difference-based defense methods? First, the distributional differences of multi-level representations on the regularly trained backdoored models are verified to be significant by introducing Maximum Mean Discrepancy (MMD), Energy Distance (ED), and Sliced Wasserstein Distance (SWD) as the metrics. Then, ML-MMDR, a difference reduction method that adds multi-level MMD regularization into the loss, is proposed, and its effectiveness is testified on three typical difference-based defense methods. Across all the experimental settings, the F1 scores of these methods drop from 90%-100% on the regularly trained backdoored models to 60%-70% on the models trained with ML-MMDR. These results indicate that the proposed MMD regularization can enhance the stealthiness of existing backdoor attack methods. The prototype code of our method is now available at https://github.com/xpf/Multi-Level-MMD-Regularization.

cs.LG↗

arXiv2022

MVD: Memory-Related Vulnerability Detection Based on Flow-Sensitive Graph Neural Networks

Memory-related vulnerabilities constitute severe threats to the security of modern software. Despite the success of deep learning-based approaches to generic vulnerability detection, they are still limited by the underutilization of flow information when applied for detecting memory-related vulnerabilities, leading to high false positives. In this paper,we propose MVD, a statement-level Memory-related Vulnerability Detection approach based on flow-sensitive graph neural networks (FS-GNN). FS-GNN is employed to jointly embed both unstructured information (i.e., source code) and structured information (i.e., control- and data-flow) to capture implicit memory-related vulnerability patterns. We evaluate MVD on the dataset which contains 4,353 real-world memory-related vulnerabilities, and compare our approach with three state-of-the-art deep learning-based approaches as well as five popular static analysisbased memory detectors. The experiment results show that MVD achieves better detection accuracy, outperforming both state-of-theart DL-based and static analysis-based approaches. Furthermore, MVD makes a great trade-off between accuracy and efficiency.

cs.CR↗

arXiv2022

ADBCMM : Acronym Disambiguation by Building Counterfactuals and Multilingual Mixing

Scientific documents often contain a large number of acronyms. Disambiguation of these acronyms will help researchers better understand the meaning of vocabulary in the documents. In the past, thanks to large amounts of data from English literature, acronym task was mainly applied in English literature. However, for other low-resource languages, this task is difficult to obtain good performance and receives less attention due to the lack of large amount of annotation data. To address the above issue, this paper proposes an new method for acronym disambiguation, named as ADBCMM, which can significantly improve the performance of low-resource languages by building counterfactuals and multilingual mixing. Specifically, by balancing data bias in low-resource langauge, ADBCMM will able to improve the test performance outside the data set. In SDU@AAAI-22 - Shared Task 2: Acronym Disambiguation, the proposed method won first place in French and Spanish. You can repeat our results here https://github.com/WENGSYX/ADBCMM.

cs.CL↗

arXiv2022

Self-Adversarial Training incorporating Forgery Attention for Image Forgery Localization

Image editing techniques enable people to modify the content of an image without leaving visual traces and thus may cause serious security risks. Hence the detection and localization of these forgeries become quite necessary and challenging. Furthermore, unlike other tasks with extensive data, there is usually a lack of annotated forged images for training due to annotation difficulties. In this paper, we propose a self-adversarial training strategy and a reliable coarse-to-fine network that utilizes a self-attention mechanism to localize forged regions in forgery images. The self-attention module is based on a Channel-Wise High Pass Filter block (CW-HPF). CW-HPF leverages inter-channel relationships of features and extracts noise features by high pass filters. Based on the CW-HPF, a self-attention mechanism, called forgery attention, is proposed to capture rich contextual dependencies of intrinsic inconsistency extracted from tampered regions. Specifically, we append two types of attention modules on top of CW-HPF respectively to model internal interdependencies in spatial dimension and external dependencies among channels. We exploit a coarse-to-fine network to enhance the noise inconsistency between original and tampered regions. More importantly, to address the issue of insufficient training data, we design a self-adversarial training strategy that expands training data dynamically to achieve more robust performance. Specifically, in each training iteration, we perform adversarial attacks against our network to generate adversarial examples and train our model on them. Extensive experimental results demonstrate that our proposed algorithm steadily outperforms state-of-the-art methods by a clear margin in different benchmark datasets.

cs.CV↗

arXiv2022

A Higher-Order Semantic Dependency Parser

Higher-order features bring significant accuracy gains in semantic dependency parsing. However, modeling higher-order features with exact inference is NP-hard. Graph neural networks (GNNs) have been demonstrated to be an effective tool for solving NP-hard problems with approximate inference in many graph learning tasks. Inspired by the success of GNNs, we investigate building a higher-order semantic dependency parser by applying GNNs. Instead of explicitly extracting higher-order features from intermediate parsing graphs, GNNs aggregate higher-order information concisely by stacking multiple GNN layers. Experimental results show that our model outperforms the previous state-of-the-art parser on the SemEval 2015 Task 18 English datasets.

cs.CL↗

arXiv2022

Carbide: Highly Reliable Networks Through Real-Time Multiple Control Plane Composition

Achieving highly reliable networks is essential for network operators to ensure proper packet delivery in the event of software errors or hardware failures. Networks must ensure reachability and routing correctness, such as subnet isolation and waypoint traversal. Existing work in network verification relies on centralized computation at the cost of fault tolerance, while other approaches either build an over-engineered, complex control plane, or compose multiple control planes without providing any guarantee on correctness. This paper presents Carbide, a novel system to achieve high reliability in networks through distributed verification and multiple control plane composition. The core of Carbide is a simple, generic, efficient distributed verification framework that transforms a generic network verification problem to a reachability verification problem on a directed acyclic graph (DAG), and solves the latter via an efficient distributed verification protocol (DV-protocol). Equipped with verification results, Carbide allows the systematic composition of multiple control planes and realization of operator-specified consistency. Carbide is fully implemented. Extensive experiments show that (1) Carbide reduces downtime by 43% over the most reliable individual underlying control plane, while enforcing correctness requirements on all traffic; and (2) by systematically decomposing computation to devices and pruning unnecessary messaging between devices during verification, Carbide scales to a production data center network.

cs.NI↗

arXiv2021

Protonation-induced discrete superconducting phases in bulk FeSe single crystals

The superconducting transition temperature, $T_{\rm{c}}$, of FeSe can be significantly enhanced several-fold by applying pressure, electron doping, intercalating spacing layer, and reducing dimensionality. Various ordered electronic phases, such as nematicity and spin density waves, have also been observed accompanying high-$T_{\rm{c}}$ superconductivity. Investigation on the evolution of the electronic structure with $T_{\rm{c}}$ is essential to understanding electronic behavior and high-$T_{\rm{c}}$ superconductivity in FeSe and its derived superconductors. In this report, we have found a series of discrete superconducting phases, with a maximum $T_{\rm{c}}$ up to 44 K, in H$^+$-intercalated FeSe single crystals using an ionic liquid gating method. Accompanied with the increase of $T_{\rm{c}}$, suppression of the nematic phase and evolution from non-Fermi-liquid to Fermi-liquid behavior was observed. An abrupt change in the Fermi surface topology was proposed to explain the discrete superconducting phases. A band structure that favors the high-$T_{\rm{c}}$ superconducting phase was also revealed.

cond-mat.supr-con↗

arXiv2021

Ultra-Fast Accurate AoA Estimation via Automotive Massive-MIMO Radar

Massive multiple-input multiple-output (MIMO) radar, enabled by millimeter-wave virtual MIMO techniques, provides great promises to the high-resolution automotive sensing and target detection in unmanned ground/aerial vehicles (UGA/UAV). As a long-established problem, however, existing subspace methods suffer from either high complexity or low accuracy. In this work, we propose two efficient methods, to accomplish fast subspace computation and accurate angle of arrival (AoA) acquisition. By leveraging randomized low-rank approximation, our fast multiple signal classification (MUSIC) methods, relying on random sampling and projection techniques, substantially accelerate the subspace estimation by orders of magnitude. Moreover, we establish the theoretical bounds of our proposed methods, which ensure the accuracy of the approximated pseudo-spectrum. As demonstrated, the pseudo-spectrum acquired by our fast-MUSIC would be highly precise; and the estimated AoA is almost as accurate as standard MUSIC. In contrast, our new methods are tremendously faster than standard MUSIC. Thus, our fast-MUSIC enables the high-resolution real-time environmental sensing with massive MIMO radars, which has great potential in the emerging unmanned systems.

eess.SP↗

arXiv2021

Learning Robust Policy against Disturbance in Transition Dynamics via State-Conservative Policy Optimization

Deep reinforcement learning algorithms can perform poorly in real-world tasks due to the discrepancy between source and target environments. This discrepancy is commonly viewed as the disturbance in transition dynamics. Many existing algorithms learn robust policies by modeling the disturbance and applying it to source environments during training, which usually requires prior knowledge about the disturbance and control of simulators. However, these algorithms can fail in scenarios where the disturbance from target environments is unknown or is intractable to model in simulators. To tackle this problem, we propose a novel model-free actor-critic algorithm -- namely, state-conservative policy optimization (SCPO) -- to learn robust policies without modeling the disturbance in advance. Specifically, SCPO reduces the disturbance in transition dynamics to that in state space and then approximates it by a simple gradient-based regularizer. The appealing features of SCPO include that it is simple to implement and does not require additional knowledge about the disturbance or specially designed simulators. Experiments in several robot control tasks demonstrate that SCPO learns robust policies against the disturbance in transition dynamics.

cs.LG↗

arXiv2021

Sample-Efficient Reinforcement Learning via Conservative Model-Based Actor-Critic

Model-based reinforcement learning algorithms, which aim to learn a model of the environment to make decisions, are more sample efficient than their model-free counterparts. The sample efficiency of model-based approaches relies on whether the model can well approximate the environment. However, learning an accurate model is challenging, especially in complex and noisy environments. To tackle this problem, we propose the conservative model-based actor-critic (CMBAC), a novel approach that achieves high sample efficiency without the strong reliance on accurate learned models. Specifically, CMBAC learns multiple estimates of the Q-value function from a set of inaccurate models and uses the average of the bottom-k estimates -- a conservative estimate -- to optimize the policy. An appealing feature of CMBAC is that the conservative estimates effectively encourage the agent to avoid unreliable "promising actions" -- whose values are high in only a small fraction of the models. Experiments demonstrate that CMBAC significantly outperforms state-of-the-art approaches in terms of sample efficiency on several challenging tasks, and the proposed method is more robust than previous methods in noisy environments.

cs.LG↗

arXiv2021

Deep Contextual Video Compression

Most of the existing neural video compression methods adopt the predictive coding framework, which first generates the predicted frame and then encodes its residue with the current frame. However, as for compression ratio, predictive coding is only a sub-optimal solution as it uses simple subtraction operation to remove the redundancy across frames. In this paper, we propose a deep contextual video compression framework to enable a paradigm shift from predictive coding to conditional coding. In particular, we try to answer the following questions: how to define, use, and learn condition under a deep video compression framework. To tap the potential of conditional coding, we propose using feature domain context as condition. This enables us to leverage the high dimension context to carry rich information to both the encoder and the decoder, which helps reconstruct the high-frequency contents for higher video quality. Our framework is also extensible, in which the condition can be flexibly designed. Experiments show that our method can significantly outperform the previous state-of-the-art (SOTA) deep video compression methods. When compared with x265 using veryslow preset, we can achieve 26.0% bitrate saving for 1080P standard test videos.

eess.IV↗

arXiv2021

Text Gestalt: Stroke-Aware Scene Text Image Super-Resolution

In the last decade, the blossom of deep learning has witnessed the rapid development of scene text recognition. However, the recognition of low-resolution scene text images remains a challenge. Even though some super-resolution methods have been proposed to tackle this problem, they usually treat text images as general images while ignoring the fact that the visual quality of strokes (the atomic unit of text) plays an essential role for text recognition. According to Gestalt Psychology, humans are capable of composing parts of details into the most similar objects guided by prior knowledge. Likewise, when humans observe a low-resolution text image, they will inherently use partial stroke-level details to recover the appearance of holistic characters. Inspired by Gestalt Psychology, we put forward a Stroke-Aware Scene Text Image Super-Resolution method containing a Stroke-Focused Module (SFM) to concentrate on stroke-level internal structures of characters in text images. Specifically, we attempt to design rules for decomposing English characters and digits at stroke-level, then pre-train a text recognizer to provide stroke-level attention maps as positional clues with the purpose of controlling the consistency between the generated super-resolution image and high-resolution ground truth. The extensive experimental results validate that the proposed method can indeed generate more distinguishable images on TextZoom and manually constructed Chinese character dataset Degraded-IC13. Furthermore, since the proposed SFM is only used to provide stroke-level guidance when training, it will not bring any time overhead during the test phase. Code is available at https://github.com/FudanVI/FudanOCR/tree/main/text-gestalt.

cs.CV↗