arXiv subjects

Qin Wang

Publications and source records attributed to Qin Wang.

At least 181 records · Page 10Linked to original sources

arXiv2022

Revisiting Deep Semi-supervised Learning: An Empirical Distribution Alignment Framework and Its Generalization Bound

In this work, we revisit the semi-supervised learning (SSL) problem from a new perspective of explicitly reducing empirical distribution mismatch between labeled and unlabeled samples. Benefited from this new perspective, we first propose a new deep semi-supervised learning framework called Semi-supervised Learning by Empirical Distribution Alignment (SLEDA), in which existing technologies from the domain adaptation community can be readily used to address the semi-supervised learning problem through reducing the empirical distribution distance between labeled and unlabeled data. Based on this framework, we also develop a new theoretical generalization bound for the research community to better understand the semi-supervised learning problem, in which we show the generalization error of semi-supervised learning can be effectively bounded by minimizing the training error on labeled data and the empirical distribution distance between labeled and unlabeled data. Building upon our new framework and the theoretical bound, we develop a simple and effective deep semi-supervised learning method called Augmented Distribution Alignment Network (ADA-Net) by simultaneously adopting the well-established adversarial training strategy from the domain adaptation community and a simple sample interpolation strategy for data augmentation. Additionally, we incorporate both strategies in our ADA-Net into two exiting SSL methods to further improve their generalization capability, which indicates that our new framework provides a complementary solution for solving the SSL problem. Our comprehensive experimental results on two benchmark datasets SVHN and CIFAR-10 for the semi-supervised image recognition task and another two benchmark datasets ModelNet40 and ShapeNet55 for the semi-supervised point cloud recognition task demonstrate the effectiveness of our proposed framework for SSL.

cs.CV↗

arXiv2021

Integrating Expert Knowledge with Domain Adaptation for Unsupervised Fault Diagnosis

Data-driven fault diagnosis methods often require abundant labeled examples for each fault type. On the contrary, real-world data is often unlabeled and consists of mostly healthy observations and only few samples of faulty conditions. The lack of labels and fault samples imposes a significant challenge for existing data-driven fault diagnosis methods. In this paper, we aim to overcome this limitation by integrating expert knowledge with domain adaptation in a synthetic-to-real framework for unsupervised fault diagnosis. Motivated by the fact that domain experts often have a relatively good understanding on how different fault types affect healthy signals, in the first step of the proposed framework, a synthetic fault dataset is generated by augmenting real vibration samples of healthy bearings. This synthetic dataset integrates expert knowledge and encodes class information about the fault types. However, models trained solely based on the synthetic data often do not perform well because of the distinct distribution difference between the synthetically generated and real faults. To overcome this domain gap between the synthetic and real data, in the second step of the proposed framework, an imbalance-robust domain adaptation~(DA) approach is proposed to adapt the model from synthetic faults~(source) to the unlabeled real faults~(target) which suffer from severe class imbalance. The framework is evaluated on two unsupervised fault diagnosis cases for bearings, the CWRU laboratory dataset and a real-world wind-turbine dataset. Experimental results demonstrate that the generated faults are effective for encoding fault type information and the domain adaptation is robust against the different levels of class imbalance between faults.

eess.SP↗

arXiv2021

K-theory of the maximal and reduced Roe algebras of metric spaces with A-by-CE coarse fibrations

Let $X$ be a discrete metric space with bounded geometry. We show that if $X$ admits an "A-by-CE coarse fibration", then the canonical quotient map $λ: C^*_{\max}(X)\to C^*(X)$ from the maximal Roe algebra to the Roe algebra of $X$, and the canonical quotient map $λ: C^*_{u, \max}(X)\to C^*_u(X)$ from the maximal uniform Roe algebra to the uniform Roe algebra of $X$, induce isomorphisms on $K$-theory. A typical example of such a space arises from a sequence of group extensions $\{1\to N_n\to G_n\to Q_n\to 1\}$ such that the sequence $\{N_n\}$ has Yu's property A, and the sequence $\{Q_n\}$ admits a coarse embedding into Hilbert space. This extends an early result of J. Špakula and R. Willett \cite{JR2013} to the case of metric spaces which may not admit a coarse embedding into Hilbert space. Moreover, it implies that the maximal coarse Baum-Connes conjecture holds for a large class of metric spaces which may not admit a fibred coarse embedding into Hilbert space.

math.OA↗

arXiv2021

Non-Fungible Token (NFT): Overview, Evaluation, Opportunities and Challenges

The Non-Fungible Token (NFT) market is mushrooming in recent years. The concept of NFT originally comes from a token standard of Ethereum, aiming to distinguish each token with distinguishable signs. This type of token can be bound with virtual/digital properties as their unique identifications. With NFTs, all marked properties can be freely traded with customized values according to their ages, rarity, liquidity, etc. It has greatly stimulated the prosperity of the decentralized application (DApp) market. At the time of writing (May 2021), the total money used on completed NFT sales has reached $34,530,649.86$ USD. The thousandfold return on its increasing market draws huge attention worldwide. However, the development of the NFT ecosystem is still in its early stage, and the technologies of NFTs are pre-mature. Newcomers may get lost in their frenetic evolution due to the lack of systematic summaries. In this technical report, we explore the NFT ecosystems in several aspects. We start with an overview of state-of-the-art NFT solutions, then provide their technical components, protocols, standards, and desired proprieties. Afterward, we give a security evolution, with discussions on the perspectives of their design models, opportunities, and challenges. To the best of our knowledge, this is the first systematic study on the current NFT ecosystems.

cs.CR↗

arXiv2021

The equivariant coarse Baum-Connes conjecture for metric spaces with proper group actions

The equivariant coarse Baum-Connes conjecture interpolates between the Baum-Connes conjecture for a discrete group and the coarse Baum-Connes conjecture for a proper metric space. In this paper, we study this conjecture under certain assumptions. More precisely, assume that a countable discrete group $Γ$ acts properly and isometrically on a discrete metric space $X$ with bounded geometry, not necessarily cocompact. We show that if the quotient space $X/Γ$ admits a coarse embedding into Hilbert space and $Γ$ is amenable, and that the $Γ$-orbits in $X$ are uniformly equivariantly coarsely equivalent to each other, then the equivariant coarse Baum-Connes conjecture holds for $(X, Γ)$. Along the way, we prove a $K$-theoretic amenability statement for the $Γ$-space $X$ under the same assumptions as above, namely, the canonical quotient map from the maximal equivariant Roe algebra of $X$ to the reduced equivariant Roe algebra of $X$ induces an isomorphism on $K$-theory.

math.KT↗

arXiv2021

Improving Semi-Supervised and Domain-Adaptive Semantic Segmentation with Self-Supervised Depth Estimation

Training deep networks for semantic segmentation requires large amounts of labeled training data, which presents a major challenge in practice, as labeling segmentation masks is a highly labor-intensive process. To address this issue, we present a framework for semi-supervised and domain-adaptive semantic segmentation, which is enhanced by self-supervised monocular depth estimation (SDE) trained only on unlabeled image sequences. In particular, we utilize SDE as an auxiliary task comprehensively across the entire learning framework: First, we automatically select the most useful samples to be annotated for semantic segmentation based on the correlation of sample diversity and difficulty between SDE and semantic segmentation. Second, we implement a strong data augmentation by mixing images and labels using the geometry of the scene. Third, we transfer knowledge from features learned during SDE to semantic segmentation by means of transfer and multi-task learning. And fourth, we exploit additional labeled synthetic data with Cross-Domain DepthMix and Matching Geometry Sampling to align synthetic and real data. We validate the proposed model on the Cityscapes dataset, where all four contributions demonstrate significant performance gains, and achieve state-of-the-art results for semi-supervised semantic segmentation as well as for semi-supervised domain adaptation. In particular, with only 1/30 of the Cityscapes labels, our method achieves 92% of the fully-supervised baseline performance and even 97% when exploiting additional data from GTA. The source code is available at https://github.com/lhoyer/improving_segmentation_with_selfsupervised_depth.

cs.CV↗

arXiv2021

Domain Adaptive Semantic Segmentation with Self-Supervised Depth Estimation

Domain adaptation for semantic segmentation aims to improve the model performance in the presence of a distribution shift between source and target domain. Leveraging the supervision from auxiliary tasks~(such as depth estimation) has the potential to heal this shift because many visual tasks are closely related to each other. However, such a supervision is not always available. In this work, we leverage the guidance from self-supervised depth estimation, which is available on both domains, to bridge the domain gap. On the one hand, we propose to explicitly learn the task feature correlation to strengthen the target semantic predictions with the help of target depth estimation. On the other hand, we use the depth prediction discrepancy from source and target depth decoders to approximate the pixel-wise adaptation difficulty. The adaptation difficulty, inferred from depth, is then used to refine the target semantic segmentation pseudo-labels. The proposed method can be easily implemented into existing segmentation frameworks. We demonstrate the effectiveness of our approach on the benchmark tasks SYNTHIA-to-Cityscapes and GTA-to-Cityscapes, on which we achieve the new state-of-the-art performance of $55.0\%$ and $56.6\%$, respectively. Our code is available at \url{https://qin.ee/corda}.

cs.CV↗

arXiv2021

Colorectal Polyp Classification from White-light Colonoscopy Images via Domain Alignment

Differentiation of colorectal polyps is an important clinical examination. A computer-aided diagnosis system is required to assist accurate diagnosis from colonoscopy images. Most previous studies at-tempt to develop models for polyp differentiation using Narrow-Band Imaging (NBI) or other enhanced images. However, the wide range of these models' applications for clinical work has been limited by the lagging of imaging techniques. Thus, we propose a novel framework based on a teacher-student architecture for the accurate colorectal polyp classification (CPC) through directly using white-light (WL) colonoscopy images in the examination. In practice, during training, the auxiliary NBI images are utilized to train a teacher network and guide the student network to acquire richer feature representation from WL images. The feature transfer is realized by domain alignment and contrastive learning. Eventually the final student network has the ability to extract aligned features from only WL images to facilitate the CPC task. Besides, we release the first public-available paired CPC dataset containing WL-NBI pairs for the alignment training. Quantitative and qualitative evaluation indicates that the proposed method outperforms the previous methods in CPC, improving the accuracy by 5.6%with very fast speed.

cs.CV↗

arXiv2021

Adaptive Residue-wise Profile Fusion for Low Homologous Protein SecondaryStructure Prediction Using External Knowledge

Protein secondary structure prediction (PSSP) is essential for protein function analysis. However, for low homologous proteins, the PSSP suffers from insufficient input features. In this paper, we explicitly import external self-supervised knowledge for low homologous PSSP under the guidance of residue-wise profile fusion. In practice, we firstly demonstrate the superiority of profile over Position-Specific Scoring Matrix (PSSM) for low homologous PSSP. Based on this observation, we introduce the novel self-supervised BERT features as the pseudo profile, which implicitly involves the residue distribution in all native discovered sequences as the complementary features. Further-more, a novel residue-wise attention is specially designed to adaptively fuse different features (i.e.,original low-quality profile, BERT based pseudo profile), which not only takes full advantage of each feature but also avoids noise disturbance. Be-sides, the feature consistency loss is proposed to accelerate the model learning from multiple semantic levels. Extensive experiments confirm that our method outperforms state-of-the-arts (i.e.,4.7%forextremely low homologous cases on BC40 dataset).

q-bio.QM↗

arXiv2021

Shallow Feature Matters for Weakly Supervised Object Localization

Weakly supervised object localization (WSOL) aims to localize objects by only utilizing image-level labels. Class activation maps (CAMs) are the commonly used features to achieve WSOL. However, previous CAM-based methods did not take full advantage of the shallow features, despite their importance for WSOL. Because shallow features are easily buried in background noise through conventional fusion. In this paper, we propose a simple but effective Shallow feature-aware Pseudo supervised Object Localization (SPOL) model for accurate WSOL, which makes the utmost of low-level features embedded in shallow layers. In practice, our SPOL model first generates the CAMs through a novel element-wise multiplication of shallow and deep feature maps, which filters the background noise and generates sharper boundaries robustly. Besides, we further propose a general class-agnostic segmentation model to achieve the accurate object mask, by only using the initial CAMs as the pseudo label without any extra annotation. Eventually, a bounding box extractor is applied to the object mask to locate the target. Experiments verify that our SPOL outperforms the state-of-the-art on both CUB-200 and ImageNet-1K benchmarks, achieving 93.44% and 67.15% (i.e., 3.93% and 2.13% improvement) Top-5 localization accuracy, respectively.

cs.CV↗

arXiv2021

Anonymous Blockchain-based System for Consortium

Blockchain brings various advantages to online transactions. However, the total transparency of these transactions may leakage users' sensitive information. Requirements on both cooperation and anonymity for companies/organizations become necessary. In this paper, we propose a Multi-center Anonymous Blockchain-based (MAB) system, with joint management for the consortium and privacy protection for the participants. To achieve that, we formalize the syntax used by the MAB system and present a general construction based on a modular design. By applying cryptographic primitives to each module, we instantiate our scheme with anonymity and decentralization. Furthermore, we carry out a comprehensive formal analysis of the proposed solution. The results demonstrate our constructed scheme is secure and efficient.

cs.CR↗

arXiv2021

Measurement-device-independent quantum key distribution with insecure sources

Measurement-device-independent quantum key distribution (MDI-QKD) can eliminate all detector side-channel loopholes and has shown excellent performance in long-distance secret keys sharing. Conventional security proofs, however, require additional assumptions on sources and that can be compromised through uncharacterized side channels in practice. Here, we present a general formalism based on reference technique to prove the security of MDI-QKD against any possible sources imperfection and/or side channels. With this formalism, we investigate the asymptotic performance of single-photon sources without any extra assumptions on the state preparations. Our results highlight the importance of transmitters' security.

quant-ph↗

arXiv2021

The coarse Novikov conjecture for extensions of coarsely embeddable groups

Let $(1\to N_n\to G_n\to Q_n \to 1)_{n\in \mathbb{N}}$ be a sequence of extensions of countable discrete groups. Endow $(G_n)_{n\in \mathbb{N}}$ with metrics associated to proper length functions on $(G_n)_{n\in \mathbb{N}}$ respectively such that the sequence of metric spaces $(G_n)_{n\in \mathbb{N}}$ have uniform bounded geometry. We show that if $(N_n)_{n\in \mathbb{N}}$ and $(Q_n)_{n\in \mathbb{N}}$ are coarsely embeddable into Hilbert space, then the coarse Novikov conjecture holds for the sequence $(G_n)_{n\in \mathbb{N}}$, which may not admit a coarse embedding into Hilbert space.

math.KT↗

arXiv2021

Experimental measurement-device-independent quantum key distribution with the double-scanning method

The measurement-device-independent quantum key distribution (MDI-QKD) can be immune to all detector side-channel attacks. Moreover, it can be easily implemented combining with the matured decoy-state methods under current technology. It thus seems a very promising candidate in practical implementation of quantum communications. However, it suffers from severe finite-data-size effect in most existing MDI-QKD protocols, resulting in relatively low key rates. Recently, Jiang et al. [Phys. Rev. A 103, 012402 (2021)] proposed a double-scanning method to drastically increase the key rate of MDI-QKD. Based on Jiang et al.'s theoretical work, here we for the first time implement the double-scanning method into MDI-QKD and carry out corresponding experimental demonstration. With a moderate number of pulses of 10^10, we can achieve 150 km secure transmission distance which is impossible with all former methods. Therefore, our present work paves the way towards practical implementation of MDI-QKD.

quant-ph↗

arXiv2021

An Offline Delegatable Cryptocurrency System

Blockchain-based cryptocurrencies, facilitating the convenience of payment by providing a decentralized online solution, have not been widely adopted so far due to slow confirmation of transactions. Offline delegation offers an efficient way to exchange coins. However, in such an approach, the coins that have been delegated confront the risk of being spent twice since the delegator's behaviour cannot be restricted easily on account of the absence of effective supervision. Even if a third party can be regarded as a judge between the delegator and delegatee to secure transactions, she still faces the threat of being compromised or providing misleading assure. Moreover, the approach equipped with a third party contradicts the real intention of decentralized cryptocurrency systems. In this paper, we propose \textit{DelegaCoin}, an offline delegatable cryptocurrency system to mitigate such an issue. We exploit trusted execution environments (TEEs) as decentralized "virtual agents" to prevent malicious delegation. In DelegaCoin, an owner can delegate his coins through offline-transactions without interacting with the blockchain network. A formal model and analysis, prototype implementation, and further evaluation demonstrate that our scheme is provably secure and practically feasible.

cs.CR↗

arXiv2021

Both qubits of the singlet state can be steered simultaneously by multiple independent observers via sequential measurement

Quantum correlation is a fundamental property which distinguishes quantum systems from classical ones, and it is also a fragile resource under projective measurement. Recently, it has been shown that a subsystem in entangled pairs can share nonlocality with multiple observers in sequence. Here we present a new steering scenario where both subsystems are accessible by multiple observers. And it is found that the two qubits in singlet state can be simultaneously steered by two sequential observers, respectively.

quant-ph↗

arXiv2021

Reference-frame-independent measurement-device-independent quantum key distribution with imperfect sources

Reference-frame-independent measurement-device-independent quantum key distribution (RFI-MDI-QKD) can remove all potential detector side-channel attacks and the requirement of real-time alignment of reference frames. However, all previous RFI-MDI-QKD implementations assume the perfect state preparation in sources, which is impractical and may lead to security loopholes. Here, we propose a RFI-MDI-QKD protocol which is robust against state preparation flaws. Comparing to the conventional six-state RFI-MDI-QKD, our scheme can be realized with only four flawed states, which improves the practical security of RFI-MDI-QKD and simplifies the experimental implementation. In addition, simulation results demonstrate that source flaws in Z basis have adverse effect on the performance of RFI-MDI-QKD while the source flaws in X and Y bases have almost no effect. We hope that this work could provide a valuable reference for practical implementations of RFI-MDI-QKD.

quant-ph↗

arXiv2021

Twin-field quantum key distribution with discrete-phase-randomized sources

Thanks to the single-photon interference at a third untrusted party, the twin-field quantun key distribution (TF-QKD) protocol and its variants can beat the well-known rate-loss bound without quantum repeaters, and related experiments have been implemented recently. Generally, quantum states in these schemes should be randomly switched between the code mode and test mode. To adopt the standard decoy-state method, phases of coherent state sources in the test mode are assumed to be continuously randomized. However, such a crucial assumption cannot be well satisfied in experimental implementations. In this paper, to bridge the gap between theory and practice, we propose a TF-QKD variant with discrete-phase-randomized sources both in the code mode and test mode, and prove its security against collective attacks. Our simulation results indicate that, with only a small number of discrete phases, the performance of discrete-phase-randomized sources can overcome the rate-loss bound and approach that of continuous-phase-randomized sources.

quant-ph↗