arXiv subjects

Yuan He

Publications and source records attributed to Yuan He.

At least 109 records · Page 6Linked to original sources

arXiv2022

AdaComm: Tracing Channel Dynamics for Reliable Cross-Technology Communication

Cross-Technology Communication (CTC) is an emerging technology to support direct communication between wireless devices that follow different standards. In spite of the many different proposals from the community to enable CTC, the performance aspect of CTC is an equally important problem but has seldom been studied before. We find this problem is extremely challenging, due to the following reasons: on one hand, a link for CTC is essentially different from a conventional wireless link. The conventional link indicators like RSSI (received signal strength indicator) and SNR (signal to noise ratio) cannot be used to directly characterize a CTC link. On the other hand, the indirect indicators like PER (packet error rate), which is adopted by many existing CTC proposals, cannot capture the short-term link behavior. As a result, the existing CTC proposals fail to keep reliable performance under dynamic channel conditions. In order to address the above challenge, we in this paper propose AdaComm, a generic framework to achieve self-adaptive CTC in dynamic channels. Instead of reactively adjusting the CTC sender, AdaComm adopts online learning mechanism to adaptively adjust the decoding model at the CTC receiver. The self-adaptive decoding model automatically learns the effective features directly from the raw received signals that are embedded with the current channel state. With the lossless channel information, AdaComm further adopts the fine tuning and full training modes to cope with the continuous and abrupt channel dynamics. We implement AdaComm and integrate it with two existing CTC approaches that respectively employ CSI (channel state information) and RSSI as the information carrier. The evaluation results demonstrate that AdaComm can significantly reduce the SER (symbol error rate) by 72.9% and 49.2%, respectively, compared with the existing approaches.

cs.NI↗

arXiv2022

MotorBeat: Acoustic Communication for Home Appliances via Variable Pulse Width Modulation

More and more home appliances are now connected to the Internet, thus enabling various smart home applications. However, a critical problem that may impede the further development of smart home is overlooked: Small appliances account for the majority of home appliances, but they receive little attention and most of them are cut off from the Internet. To fill this gap, we propose MotorBeat, an acoustic communication approach that connects small appliances to a smart speaker. Our key idea is to exploit direct current (DC) motors, which are common components of small appliances, to transmit acoustic messages. We design a novel scheme named Variable Pulse Width Modulation (V-PWM) to drive DC motors. MotorBeat achieves the following 3C goals: (1) Comfortable to hear, (2) Compatible with multiple motor modes, and (3) Concurrent transmission. We implement MotorBeat with commercial devices and evaluate its performance on three small appliances and ten DC motors. The results show that the communication range can be up to 10 m

cs.NI↗

arXiv2022

FoVR: Attention-based VR Streaming through Bandwidth-limited Wireless Networks

Consumer Virtual Reality (VR) has been widely used in various application areas, such as entertainment and medicine. In spite of the superb immersion experience, to enable high-quality VR on untethered mobile devices remains an extremely challenging task. The high bandwidth demands of VR streaming generally overburden a conventional wireless connection, which affects the user experience and in turn limits the usability of VR in practice. In this paper, we propose FoVR, attention-based hierarchical VR streaming through bandwidth-limited wireless networks. The design of FoVR stems from the insight that human's vision is hierarchical, so that different areas in the field of view (FoV) can be served with VR content of different qualities. By exploiting the gaze tracking capacity of the VR devices, FoVR is able to accurately predict the user's attention so that the streaming of hierarchical VR can be appropriately scheduled. In this way, FoVR significantly reduces the bandwidth cost and computing cost while keeping high quality of user experience. We implement FoVR on a commercial VR device and evaluate its performance in various scenarios. The experiment results show that FoVR reduces the bandwidth cost by 88.9% and 76.2%, respectively compared to the original VR streaming and the state-of-the-art approach.

cs.NI↗

arXiv2022

Wi-attack: Cross-technology Impersonation Attack against iBeacon Services

iBeacon protocol is widely deployed to provide location-based services. By receiving its BLE advertisements, nearby devices can estimate the proximity to the iBeacon or calculate indoor positions. However, the open nature of these advertisements brings vulnerability to impersonation attacks. Such attacks could lead to spam, unreliable positioning, and even security breaches. In this paper, we propose Wi-attack, revealing the feasibility of using WiFi devices to conduct impersonation attacks on iBeacon services. Different from impersonation attacks using BLE compatible hardware, Wi-attack is not restricted by broadcasting intervals and is able to impersonate multiple iBeacons at the same time. Effective attacks can be launched on iBeacon services without modifications to WiFi hardware or firmware. To enable direct communication from WiFi to BLE, we use the digital emulation technique of cross technology communication. To enhance the packet reception along with its stability, we add redundant packets to eliminate cyclic prefix error entirely. The emulation provides an iBeacon packet reception rate up to 66.2%. We conduct attacks on three iBeacon services scenarios, point deployment, multilateration, and fingerprint-based localization. The evaluation results show that Wi-attack can bring an average distance error of more than 20 meters on fingerprint-based localization using only 3 APs.

cs.CR↗

arXiv2022

Continuous Gaze Tracking With Implicit Saliency-Aware Calibration on Mobile Devices

Gaze tracking is a useful human-to-computer interface, which plays an increasingly important role in a range of mobile applications. Gaze calibration is an indispensable component of gaze tracking, which transforms the eye coordinates to the screen coordinates. The existing approaches of gaze tracking either have limited accuracy or require the user's cooperation in calibration and in turn hurt the quality of experience. We in this paper propose vGaze, continuous gaze tracking with implicit saliency-aware calibration on mobile devices. The design of vGaze stems from our insight on the temporal and spatial dependent relation between the visual saliency and the user's gaze. vGaze is implemented as a light-weight software that identifies video frames with "useful" saliency information, sensing the user's head movement, performs opportunistic calibration using only those "useful" frames, and leverages historical information for accelerating saliency detection. We implement vGaze on a commercial mobile device and evaluate its performance in various scenarios. The results show that vGaze can work at real time with video playback applications. The average error of gaze tracking is 1.51 cm (2.884 degree) which decreases to 0.99 cm (1.891 degree) with historical information and 0.57 cm (1.089 degree) with an indicator.

cs.HC↗

arXiv2022

Exploring the Algorithm-Dependent Generalization of AUPRC Optimization with List Stability

Stochastic optimization of the Area Under the Precision-Recall Curve (AUPRC) is a crucial problem for machine learning. Although various algorithms have been extensively studied for AUPRC optimization, the generalization is only guaranteed in the multi-query case. In this work, we present the first trial in the single-query generalization of stochastic AUPRC optimization. For sharper generalization bounds, we focus on algorithm-dependent generalization. There are both algorithmic and theoretical obstacles to our destination. From an algorithmic perspective, we notice that the majority of existing stochastic estimators are biased only when the sampling strategy is biased, and is leave-one-out unstable due to the non-decomposability. To address these issues, we propose a sampling-rate-invariant unbiased stochastic estimator with superior stability. On top of this, the AUPRC optimization is formulated as a composition optimization problem, and a stochastic algorithm is proposed to solve this problem. From a theoretical perspective, standard techniques of the algorithm-dependent generalization analysis cannot be directly applied to such a listwise compositional optimization problem. To fill this gap, we extend the model stability from instancewise losses to listwise losses and bridge the corresponding generalization and stability. Additionally, we construct state transition matrices to describe the recurrence of the stability, and simplify calculations by matrix spectrum. Practically, experimental results on three image retrieval datasets on speak to the effectiveness and soundness of our framework.

cs.LG↗

arXiv2022

MaxMatch: Semi-Supervised Learning with Worst-Case Consistency

In recent years, great progress has been made to incorporate unlabeled data to overcome the inefficiently supervised problem via semi-supervised learning (SSL). Most state-of-the-art models are based on the idea of pursuing consistent model predictions over unlabeled data toward the input noise, which is called consistency regularization. Nonetheless, there is a lack of theoretical insights into the reason behind its success. To bridge the gap between theoretical and practical results, we propose a worst-case consistency regularization technique for SSL in this paper. Specifically, we first present a generalization bound for SSL consisting of the empirical loss terms observed on labeled and unlabeled training data separately. Motivated by this bound, we derive an SSL objective that minimizes the largest inconsistency between an original unlabeled sample and its multiple augmented variants. We then provide a simple but effective algorithm to solve the proposed minimax problem, and theoretically prove that it converges to a stationary point. Experiments on five popular benchmark datasets validate the effectiveness of our proposed method.

cs.LG↗

arXiv2022

Optimizing Partial Area Under the Top-k Curve: Theory and Practice

Top-k error has become a popular metric for large-scale classification benchmarks due to the inevitable semantic ambiguity among classes. Existing literature on top-k optimization generally focuses on the optimization method of the top-k objective, while ignoring the limitations of the metric itself. In this paper, we point out that the top-k objective lacks enough discrimination such that the induced predictions may give a totally irrelevant label a top rank. To fix this issue, we develop a novel metric named partial Area Under the top-k Curve (AUTKC). Theoretical analysis shows that AUTKC has a better discrimination ability, and its Bayes optimal score function could give a correct top-K ranking with respect to the conditional probability. This shows that AUTKC does not allow irrelevant labels to appear in the top list. Furthermore, we present an empirical surrogate risk minimization framework to optimize the proposed metric. Theoretically, we present (1) a sufficient condition for Fisher consistency of the Bayes optimal score function; (2) a generalization upper bound which is insensitive to the number of classes under a simple hyperparameter setting. Finally, the experimental results on four benchmark datasets validate the effectiveness of our proposed framework.

cs.LG↗

arXiv2022

AdAUC: End-to-end Adversarial AUC Optimization Against Long-tail Problems

It is well-known that deep learning models are vulnerable to adversarial examples. Existing studies of adversarial training have made great progress against this challenge. As a typical trait, they often assume that the class distribution is overall balanced. However, long-tail datasets are ubiquitous in a wide spectrum of applications, where the amount of head class instances is larger than the tail classes. Under such a scenario, AUC is a much more reasonable metric than accuracy since it is insensitive toward class distribution. Motivated by this, we present an early trial to explore adversarial training methods to optimize AUC. The main challenge lies in that the positive and negative examples are tightly coupled in the objective function. As a direct result, one cannot generate adversarial examples without a full scan of the dataset. To address this issue, based on a concavity regularization scheme, we reformulate the AUC optimization problem as a saddle point problem, where the objective becomes an instance-wise function. This leads to an end-to-end training protocol. Furthermore, we provide a convergence guarantee of the proposed algorithm. Our analysis differs from the existing studies since the algorithm is asked to generate adversarial examples by calculating the gradient of a min-max problem. Finally, the extensive experimental results show the performance and robustness of our algorithm in three long-tail datasets.

cs.LG↗

arXiv2022

Optimizing Two-way Partial AUC with an End-to-end Framework

The Area Under the ROC Curve (AUC) is a crucial metric for machine learning, which evaluates the average performance over all possible True Positive Rates (TPRs) and False Positive Rates (FPRs). Based on the knowledge that a skillful classifier should simultaneously embrace a high TPR and a low FPR, we turn to study a more general variant called Two-way Partial AUC (TPAUC), where only the region with $\mathsf{TPR} \ge α, \mathsf{FPR} \le β$ is included in the area. Moreover, recent work shows that the TPAUC is essentially inconsistent with the existing Partial AUC metrics where only the FPR range is restricted, opening a new problem to seek solutions to leverage high TPAUC. Motivated by this, we present the first trial in this paper to optimize this new metric. The critical challenge along this course lies in the difficulty of performing gradient-based optimization with end-to-end stochastic training, even with a proper choice of surrogate loss. To address this issue, we propose a generic framework to construct surrogate optimization problems, which supports efficient end-to-end training with deep learning. Moreover, our theoretical analyses show that: 1) the objective function of the surrogate problems will achieve an upper bound of the original problem under mild conditions, and 2) optimizing the surrogate problems leads to good generalization performance in terms of TPAUC with a high probability. Finally, empirical studies over several benchmark datasets speak to the efficacy of our framework.

cs.LG↗

arXiv2022

Cosmological-model-independent tests of cosmic distance duality relation with Type Ia supernovae and radio quasars

In this paper, we investigate the possible deviations of the cosmic distance duality relation (CDDR) using the combination of the largest SNe Ia (Pantheon) and compact radio quasar (QSO) samples through two model-independent approaches. The deviation of CDDR is written as $D_L(z)/D_A(z)(1+z)^{-2}=η(z)$ and $η(z)=e^{τ(z)/2}$, with the parameterizations of $F_1$ ($τ(z) = 2ε_1 z$) and $F_2$ ($τ(z) = (1+z)^{2ε_2}-1$). Furthermore, in order to compare the two resulting distances, two cosmological-model-independent methods, i.e., the nearby SNe Ia method and the GP method are employed to match the two distinct data at the same redshift. Our findings indicate that, compared with the results obtained in the literature, there is an improvement in precision when the latest SNe Ia and QSO samples are used. Specially, in the framework of nearby SNe Ia method, the CDDR would be constrained at the precision of $Δε_{1} = 0.013$ in Model $F_1$ and $Δε_{2}=0.018$ in Model $F_2$. Regarding the GP method, one observes that a larger data size would produce more stringent constraints on the CDDR parameters. Therefore, accompanied by further developments in cosmological observations and the analysis methods, our analysis provides an insight into the evidence for unaccounted opacity sources at an earlier stage of the universe, or at the very least the new physics involved.

astro-ph.CO↗

arXiv2022

Towards Robust Vision Transformer

Recent advances on Vision Transformer (ViT) and its improved variants have shown that self-attention-based networks surpass traditional Convolutional Neural Networks (CNNs) in most vision tasks. However, existing ViTs focus on the standard accuracy and computation cost, lacking the investigation of the intrinsic influence on model robustness and generalization. In this work, we conduct systematic evaluation on components of ViTs in terms of their impact on robustness to adversarial examples, common corruptions and distribution shifts. We find some components can be harmful to robustness. By using and combining robust components as building blocks of ViTs, we propose Robust Vision Transformer (RVT), which is a new vision transformer and has superior performance with strong robustness. We further propose two new plug-and-play techniques called position-aware attention scaling and patch-wise augmentation to augment our RVT, which we abbreviate as RVT*. The experimental results on ImageNet and six robustness benchmarks show the advanced robustness and generalization ability of RVT compared with previous ViTs and state-of-the-art CNNs. Furthermore, RVT-S* also achieves Top-1 rank on multiple robustness leaderboards including ImageNet-C and ImageNet-Sketch. The code will be available at \url{https://github.com/alibaba/easyrobust}.

cs.CV↗

arXiv2022

BERTMap: A BERT-based Ontology Alignment System

Ontology alignment (a.k.a ontology matching (OM)) plays a critical role in knowledge integration. Owing to the success of machine learning in many domains, it has been applied in OM. However, the existing methods, which often adopt ad-hoc feature engineering or non-contextual word embeddings, have not yet outperformed rule-based systems especially in an unsupervised setting. In this paper, we propose a novel OM system named BERTMap which can support both unsupervised and semi-supervised settings. It first predicts mappings using a classifier based on fine-tuning the contextual embedding model BERT on text semantics corpora extracted from ontologies, and then refines the mappings through extension and repair by utilizing the ontology structure and logic. Our evaluation with three alignment tasks on biomedical ontologies demonstrates that BERTMap can often perform better than the leading OM systems LogMap and AML.

cs.AI↗

arXiv2022

RMGN: A Regional Mask Guided Network for Parser-free Virtual Try-on

Virtual try-on(VTON) aims at fitting target clothes to reference person images, which is widely adopted in e-commerce.Existing VTON approaches can be narrowly categorized into Parser-Based(PB) and Parser-Free(PF) by whether relying on the parser information to mask the persons' clothes and synthesize try-on images. Although abandoning parser information has improved the applicability of PF methods, the ability of detail synthesizing has also been sacrificed. As a result, the distraction from original cloth may persistin synthesized images, especially in complicated postures and high resolution applications. To address the aforementioned issue, we propose a novel PF method named Regional Mask Guided Network(RMGN). More specifically, a regional mask is proposed to explicitly fuse the features of target clothes and reference persons so that the persisted distraction can be eliminated. A posture awareness loss and a multi-level feature extractor are further proposed to handle the complicated postures and synthesize high resolution images. Extensive experiments demonstrate that our proposed RMGN outperforms both state-of-the-art PB and PF methods.Ablation studies further verify the effectiveness ofmodules in RMGN.

cs.CV↗

arXiv2022

Diverse Instance Discovery: Vision-Transformer for Instance-Aware Multi-Label Image Recognition

Previous works on multi-label image recognition (MLIR) usually use CNNs as a starting point for research. In this paper, we take pure Vision Transformer (ViT) as the research base and make full use of the advantages of Transformer with long-range dependency modeling to circumvent the disadvantages of CNNs limited to local receptive field. However, for multi-label images containing multiple objects from different categories, scales, and spatial relations, it is not optimal to use global information alone. Our goal is to leverage ViT's patch tokens and self-attention mechanism to mine rich instances in multi-label images, named diverse instance discovery (DiD). To this end, we propose a semantic category-aware module and a spatial relationship-aware module, respectively, and then combine the two by a re-constraint strategy to obtain instance-aware attention maps. Finally, we propose a weakly supervised object localization-based approach to extract multi-scale local features, to form a multi-view pipeline. Our method requires only weakly supervised information at the label level, no additional knowledge injection or other strongly supervised information is required. Experiments on three benchmark datasets show that our method significantly outperforms previous works and achieves state-of-the-art results under fair experimental comparisons.

cs.CV↗

arXiv2022

Cross-Technology Communication for the Internet of Things: A Survey

The ever-developing Internet of Things (IoT) brings the prosperity of wireless sensing and control applications. In many scenarios, different wireless technologies coexist in the shared frequency medium as well as the physical space. Such wireless coexistence may lead to serious cross-technology interference (CTI) problems, e.g. channel competition, signal collision, throughput degradation. Compared with traditional methods like interference avoidance, tolerance, and concurrency mechanism, direct and timely information exchange among heterogeneous devices is therefore a fundamental requirement to ensure the usability, inter-operability, and reliability of the IoT. Under this circumstance, Cross-Technology Communication (CTC) technique thus becomes a hot topic in both academic and industrial fields, which aims at directly exchanging data among heterogeneous devices that follow different standards. This paper comprehensively summarizes the CTC techniques and reveals that the key challenge for CTC lies in the heterogeneity of IoT devices, including the incompatibility of technical standards and the asymmetry of connection capability. Based on the above finding, we present a taxonomy of the existing CTC works (packet-level CTCs and physical-level CTCs) and compare the existing CTC techniques in terms of throughput, reliability, hardware modification, and concurrency.

cs.NI↗

arXiv2022

Beyond ImageNet Attack: Towards Crafting Adversarial Examples for Black-box Domains

Adversarial examples have posed a severe threat to deep neural networks due to their transferable nature. Currently, various works have paid great efforts to enhance the cross-model transferability, which mostly assume the substitute model is trained in the same domain as the target model. However, in reality, the relevant information of the deployed model is unlikely to leak. Hence, it is vital to build a more practical black-box threat model to overcome this limitation and evaluate the vulnerability of deployed models. In this paper, with only the knowledge of the ImageNet domain, we propose a Beyond ImageNet Attack (BIA) to investigate the transferability towards black-box domains (unknown classification tasks). Specifically, we leverage a generative model to learn the adversarial function for disrupting low-level features of input images. Based on this framework, we further propose two variants to narrow the gap between the source and target domains from the data and model perspectives, respectively. Extensive experiments on coarse-grained and fine-grained domains demonstrate the effectiveness of our proposed methods. Notably, our methods outperform state-of-the-art approaches by up to 7.71\% (towards coarse-grained domains) and 25.91\% (towards fine-grained domains) on average. Our code is available at \url{https://github.com/qilong-zhang/Beyond-ImageNet-Attack}.

cs.CV↗

arXiv2022

Reading-strategy Inspired Visual Representation Learning for Text-to-Video Retrieval

This paper aims for the task of text-to-video retrieval, where given a query in the form of a natural-language sentence, it is asked to retrieve videos which are semantically relevant to the given query, from a great number of unlabeled videos. The success of this task depends on cross-modal representation learning that projects both videos and sentences into common spaces for semantic similarity computation. In this work, we concentrate on video representation learning, an essential component for text-to-video retrieval. Inspired by the reading strategy of humans, we propose a Reading-strategy Inspired Visual Representation Learning (RIVRL) to represent videos, which consists of two branches: a previewing branch and an intensive-reading branch. The previewing branch is designed to briefly capture the overview information of videos, while the intensive-reading branch is designed to obtain more in-depth information. Moreover, the intensive-reading branch is aware of the video overview captured by the previewing branch. Such holistic information is found to be useful for the intensive-reading branch to extract more fine-grained features. Extensive experiments on three datasets are conducted, where our model RIVRL achieves a new state-of-the-art on TGIF and VATEX. Moreover, on MSR-VTT, our model using two video features shows comparable performance to the state-of-the-art using seven video features and even outperforms models pre-trained on the large-scale HowTo100M dataset.

cs.CV↗