arXiv subjects

Yu Tian

Publications and source records attributed to Yu Tian.

At least 271 records · Page 15Linked to original sources

arXiv2022

Unifying information propagation models on networks and influence maximization

Information propagation on networks is a central theme in social, behavioral, and economic sciences, with important theoretical and practical implications, such as the influence maximization problem for viral marketing. Here, we consider a model that unifies the classical independent cascade models and the linear threshold models, and generalise them by considering continuous variables and allowing feedback in the dynamics. We then formulate its influence maximization as a mixed integer nonlinear programming problem and adopt derivative-free methods. Furthermore, we show that the problem can be exactly solved in the special case of linear dynamics, where the selection criterion is closely related to the Katz centrality, and propose a customized direct search method with local convergence. We then demonstrate the close-to-optimal performance of the customized direct search numerically on both synthetic and real networks.

cs.SI↗

arXiv2022

Multi-view Local Co-occurrence and Global Consistency Learning Improve Mammogram Classification Generalisation

When analysing screening mammograms, radiologists can naturally process information across two ipsilateral views of each breast, namely the cranio-caudal (CC) and mediolateral-oblique (MLO) views. These multiple related images provide complementary diagnostic information and can improve the radiologist's classification accuracy. Unfortunately, most existing deep learning systems, trained with globally-labelled images, lack the ability to jointly analyse and integrate global and local information from these multiple views. By ignoring the potentially valuable information present in multiple images of a screening episode, one limits the potential accuracy of these systems. Here, we propose a new multi-view global-local analysis method that mimics the radiologist's reading procedure, based on a global consistency learning and local co-occurrence learning of ipsilateral views in mammograms. Extensive experiments show that our model outperforms competing methods, in terms of classification accuracy and generalisation, on a large-scale private dataset and two publicly available datasets, where models are exclusively trained and tested with global labels.

cs.CV↗

arXiv2022

Experimental Realization of a Quantum Refrigerator Driven by Indefinite Causal Orders

Indefinite causal order (ICO) is playing a key role in recent quantum technologies. Here, we experimentally study quantum thermodynamics driven by ICO on nuclear spins using the nuclear magnetic resonance system. We realize the ICO of two thermalizing channels to exhibit how the mechanism works, and show that the working substance can be cooled or heated albeit it undergoes thermal contacts with reservoirs of the same temperature. Moreover, we construct a single cycle of the ICO refrigerator based on the Maxwell's demon mechanism, and evaluate its performance by measuring the work consumption and the heat energy extracted from the low-temperature reservoir. Unlike classical refrigerators in which the coefficient of performance (COP) is perversely higher the closer the temperature of the high-temperature and low-temperature reservoirs are to each other, the ICO refrigerator's COP is always bounded to small values due to the non-unit success probability in projecting the ancillary qubit to the preferable subspace. To enhance the COP, we propose and experimentally demonstrate a general framework based on the density matrix exponentiation (DME) approach, as an extension to the ICO refrigeration. The COP is observed to be enhanced by more than three times with the DME approach. Our work demonstrates a new way for non-classical heat exchange, and paves the way towards construction of quantum refrigerators on a quantum system.

quant-ph↗

arXiv2022

Pixel-wise Energy-biased Abstention Learning for Anomaly Segmentation on Complex Urban Driving Scenes

State-of-the-art (SOTA) anomaly segmentation approaches on complex urban driving scenes explore pixel-wise classification uncertainty learned from outlier exposure, or external reconstruction models. However, previous uncertainty approaches that directly associate high uncertainty to anomaly may sometimes lead to incorrect anomaly predictions, and external reconstruction models tend to be too inefficient for real-time self-driving embedded systems. In this paper, we propose a new anomaly segmentation method, named pixel-wise energy-biased abstention learning (PEBAL), that explores pixel-wise abstention learning (AL) with a model that learns an adaptive pixel-level anomaly class, and an energy-based model (EBM) that learns inlier pixel distribution. More specifically, PEBAL is based on a non-trivial joint training of EBM and AL, where EBM is trained to output high-energy for anomaly pixels (from outlier exposure) and AL is trained such that these high-energy pixels receive adaptive low penalty for being included to the anomaly class. We extensively evaluate PEBAL against the SOTA and show that it achieves the best performance across four benchmarks. Code is available at https://github.com/tianyu0207/PEBAL.

cs.CV↗

arXiv2022

Artifact-Tolerant Clustering-Guided Contrastive Embedding Learning for Ophthalmic Images

Ophthalmic images and derivatives such as the retinal nerve fiber layer (RNFL) thickness map are crucial for detecting and monitoring ophthalmic diseases (e.g., glaucoma). For computer-aided diagnosis of eye diseases, the key technique is to automatically extract meaningful features from ophthalmic images that can reveal the biomarkers (e.g., RNFL thinning patterns) linked to functional vision loss. However, representation learning from ophthalmic images that links structural retinal damage with human vision loss is non-trivial mostly due to large anatomical variations between patients. The task becomes even more challenging in the presence of image artifacts, which are common due to issues with image acquisition and automated segmentation. In this paper, we propose an artifact-tolerant unsupervised learning framework termed EyeLearn for learning representations of ophthalmic images. EyeLearn has an artifact correction module to learn representations that can best predict artifact-free ophthalmic images. In addition, EyeLearn adopts a clustering-guided contrastive learning strategy to explicitly capture the intra- and inter-image affinities. During training, images are dynamically organized in clusters to form contrastive samples in which images in the same or different clusters are encouraged to learn similar or dissimilar representations, respectively. To evaluate EyeLearn, we use the learned representations for visual field prediction and glaucoma detection using a real-world ophthalmic image dataset of glaucoma patients. Extensive experiments and comparisons with state-of-the-art methods verified the effectiveness of EyeLearn for learning optimal feature representations from ophthalmic images.

cs.CV↗

arXiv2022

Dynamical transitions in scalarization and descalarization through black hole accretion

We present the first fully nonlinear study on the accretion of scalar fields onto a seed black hole in anti-de Sitter spacetime in Einstein-Maxwell-scalar theory. Intrinsic critical phenomena in the dynamical transition between the bald and scalarized black holes are disclosed. In scalarizations, the transition is discontinuous and a metastable black hole acts as an attractor at the threshold. We construct a new physical mechanism to dynamically descalarize an isolated scalarized black hole. The first results on critical phenomena in descalarizations are revealed. The dynamical descalarizations can be either discontinuous or continuous at the threshold, distinguished by whether or not an attractor appears.

gr-qc↗

arXiv2022

NVUM: Non-Volatile Unbiased Memory for Robust Medical Image Classification

Real-world large-scale medical image analysis (MIA) datasets have three challenges: 1) they contain noisy-labelled samples that affect training convergence and generalisation, 2) they usually have an imbalanced distribution of samples per class, and 3) they normally comprise a multi-label problem, where samples can have multiple diagnoses. Current approaches are commonly trained to solve a subset of those problems, but we are unaware of methods that address the three problems simultaneously. In this paper, we propose a new training module called Non-Volatile Unbiased Memory (NVUM), which non-volatility stores running average of model logits for a new regularization loss on noisy multi-label problem. We further unbias the classification prediction in NVUM update for imbalanced learning problem. We run extensive experiments to evaluate NVUM on new benchmarks proposed by this paper, where training is performed on noisy multi-label imbalanced chest X-ray (CXR) training sets, formed by Chest-Xray14 and CheXpert, and the testing is performed on the clean multi-label CXR datasets OpenI and PadChest. Our method outperforms previous state-of-the-art CXR classifiers and previous methods that can deal with noisy labels on all evaluations. Our code is available at https://github.com/FBLADL/NVUM.

cs.CV↗

arXiv2022

Coarse-to-Fine: Hierarchical Multi-task Learning for Natural Language Understanding

Generalized text representations are the foundation of many natural language understanding tasks. To fully utilize the different corpus, it is inevitable that models need to understand the relevance among them. However, many methods ignore the relevance and adopt a single-channel model (a coarse paradigm) directly for all tasks, which lacks enough rationality and interpretation. In addition, some existing works learn downstream tasks by stitches skill block(a fine paradigm), which might cause irrationalresults due to its redundancy and noise. Inthis work, we first analyze the task correlation through three different perspectives, i.e., data property, manual design, and model-based relevance, based on which the similar tasks are grouped together. Then, we propose a hierarchical framework with a coarse-to-fine paradigm, with the bottom level shared to all the tasks, the mid-level divided to different groups, and the top-level assigned to each of the tasks. This allows our model to learn basic language properties from all tasks, boost performance on relevant tasks, and reduce the negative impact from irrelevant tasks. Our experiments on 13 benchmark datasets across five natural language understanding tasks demonstrate the superiority of our method.

cs.CL↗

arXiv2022

Face Anti-Spoofing by Learning Polarization Cues in a Real-World Scenario

Face anti-spoofing is the key to preventing security breaches in biometric recognition applications. Existing software-based and hardware-based face liveness detection methods are effective in constrained environments or designated datasets only. Deep learning method using RGB and infrared images demands a large amount of training data for new attacks. In this paper, we present a face anti-spoofing method in a real-world scenario by automatic learning the physical characteristics in polarization images of a real face compared to a deceptive attack. A computational framework is developed to extract and classify the unique face features using convolutional neural networks and SVM together. Our real-time polarized face anti-spoofing (PAAS) detection method uses a on-chip integrated polarization imaging sensor with optimized processing algorithms. Extensive experiments demonstrate the advantages of the PAAS technique to counter diverse face spoofing attacks (print, replay, mask) in uncontrolled indoor and outdoor conditions by learning polarized face images of 33 people. A four-directional polarized face image dataset is released to inspire future applications within biometric anti-spoofing field.

cs.CV↗

arXiv2022

Preserving Entanglement in a Solid-Spin System Using Quantum Autoencoders

Entanglement, as a key resource for modern quantum technologies, is extremely fragile due to the decoherence. Here, we show that a quantum autoencoder, which is trained to compress a particular set of quantum entangled states into a subspace that is robust to decoherence, can be employed to preserve entanglement. The training process is based on a hybrid quantum-classical approach to improve the efficiency in building the autoencoder and reduce the experimental errors during the optimization. Using nitrogen-vacancy centers in diamond, we demonstrate that the entangled states between the electron and nuclear spins can be encoded into the nucleus subspace which has much longer coherence time. As a result, lifetime of the Bell states in this solid-spin system is extended from 2.22 {\pm} 0.43 μs to 3.03 {\pm} 0.56 ms, yielding a three orders of magnitude improvement. The quantum autoencoder approach is universal, paving the way of utilizing long lifetime nuclear spins as immediate-access quantum memories in quantum information tasks.

quant-ph↗

arXiv2022

Contrastive Transformer-based Multiple Instance Learning for Weakly Supervised Polyp Frame Detection

Current polyp detection methods from colonoscopy videos use exclusively normal (i.e., healthy) training images, which i) ignore the importance of temporal information in consecutive video frames, and ii) lack knowledge about the polyps. Consequently, they often have high detection errors, especially on challenging polyp cases (e.g., small, flat, or partially visible polyps). In this work, we formulate polyp detection as a weakly-supervised anomaly detection task that uses video-level labelled training data to detect frame-level polyps. In particular, we propose a novel convolutional transformer-based multiple instance learning method designed to identify abnormal frames (i.e., frames with polyps) from anomalous videos (i.e., videos containing at least one frame with polyp). In our method, local and global temporal dependencies are seamlessly captured while we simultaneously optimise video and snippet-level anomaly scores. A contrastive snippet mining method is also proposed to enable an effective modelling of the challenging polyp cases. The resulting method achieves a detection accuracy that is substantially better than current state-of-the-art approaches on a new large-scale colonoscopy video dataset introduced in this work.

cs.CV↗

arXiv2022

When Multi-Level Meets Multi-Interest: A Multi-Grained Neural Model for Sequential Recommendation

Sequential recommendation aims at identifying the next item that is preferred by a user based on their behavioral history. Compared to conventional sequential models that leverage attention mechanisms and RNNs, recent efforts mainly follow two directions for improvement: multi-interest learning and graph convolutional aggregation. Specifically, multi-interest methods such as ComiRec and MIMN, focus on extracting different interests for a user by performing historical item clustering, while graph convolution methods including TGSRec and SURGE elect to refine user preferences based on multi-level correlations between historical items. Unfortunately, neither of them realizes that these two types of solutions can mutually complement each other, by aggregating multi-level user preference to achieve more precise multi-interest extraction for a better recommendation. To this end, in this paper, we propose a unified multi-grained neural model(named MGNM) via a combination of multi-interest learning and graph convolutional aggregation. Concretely, MGNM first learns the graph structure and information aggregation paths of the historical items for a user. It then performs graph convolution to derive item representations in an iterative fashion, in which the complex preferences at different levels can be well captured. Afterwards, a novel sequential capsule network is proposed to inject the sequential patterns into the multi-interest extraction process, leading to a more precise interest learning in a multi-grained manner.

cs.IR↗

arXiv2022

Critical phenomena in dynamical scalarization of charged black hole

We report a new black hole scalarization mechanism and disclose novel dynamical critical phenomena in the process of the nonlinear accretion of the scalar field into black holes. The accretion process can transform a seed black hole into a final scalarized or bald black hole, depending on the initial parameter of the scalar field $p$. There is a critical parameter $p_{\ast}$ and near it all intermediate solutions are attracted to a critical solution and stay there for a time scaling as $T\propto-γ\ln|p-p_{\ast}|$. At late times, the solutions evolve into scalarized black holes if $p>p_{\ast}$, or bald black holes if $p<p_{\ast}$. The final masses of the resulting scalarized/bald black holes satisfy power-laws $M_{p}-M_{\pm}\propto|p-p_{\ast}|^{γ_{\pm}}$ where $M_{\pm}$ are the masses of the scalarized/bald black holes when $p\to p_\ast$ from above/below, and $γ_{\pm}$ the corresponding exponents.

gr-qc↗

arXiv2022

Design of a Biomimetic Tactile Sensor for Material Classification

Tactile sensing typically involves active exploration of unknown surfaces and objects, making it especially effective at processing the characteristics of materials and textures. A key property extracted by human tactile perception is surface roughness, which relies on measuring vibratory signals using the multi-layered fingertip structure. Existing robotic systems lack tactile sensors that are able to provide high dynamic sensing ranges, perceive material properties, and maintain a low hardware cost. In this work, we introduce the reference design and fabrication procedure of a miniature and low-cost tactile sensor consisting of a biomimetic cutaneous structure, including the artificial fingerprint, dermis, epidermis, and an embedded magnet-sensor structure which serves as a mechanoreceptor for converting mechanical information to digital signals. The presented sensor is capable of detecting high-resolution magnetic field data through the Hall effect and creating high-dimensional time-frequency domain features for material texture classification. Additionally, we investigate the effects of different superficial sensor fingerprint patterns for classifying materials through both simulation and physical experimentation. After extracting time series and frequency domain features, we assess a k-nearest neighbors classifier for distinguishing between different materials. The results from our experiments show that our biomimetic tactile sensors with fingerprint ridges can classify materials with more than 8% higher accuracy and lower variability than ridge-less sensors. These results, along with the low cost and customizability of our sensor, demonstrate high potential for lowering the barrier to entry for a wide array of robotic applications, including model-less tactile sensing for texture classification, material inspection, and object recognition.

cs.RO↗

arXiv2022

Perturbed and Strict Mean Teachers for Semi-supervised Semantic Segmentation

Consistency learning using input image, feature, or network perturbations has shown remarkable results in semi-supervised semantic segmentation, but this approach can be seriously affected by inaccurate predictions of unlabelled training images. There are two consequences of these inaccurate predictions: 1) the training based on the "strict" cross-entropy (CE) loss can easily overfit prediction mistakes, leading to confirmation bias; and 2) the perturbations applied to these inaccurate predictions will use potentially erroneous predictions as training signals, degrading consistency learning. In this paper, we address the prediction accuracy problem of consistency learning methods with novel extensions of the mean-teacher (MT) model, which include a new auxiliary teacher, and the replacement of MT's mean square error (MSE) by a stricter confidence-weighted cross-entropy (Conf-CE) loss. The accurate prediction by this model allows us to use a challenging combination of network, input data and feature perturbations to improve the consistency learning generalisation, where the feature perturbations consist of a new adversarial perturbation. Results on public benchmarks show that our approach achieves remarkable improvements over the previous SOTA methods in the field. Our code is available at https://github.com/yyliu01/PS-MT.

cs.CV↗

arXiv2022

Deep One-Class Classification via Interpolated Gaussian Descriptor

One-class classification (OCC) aims to learn an effective data description to enclose all normal training samples and detect anomalies based on the deviation from the data description. Current state-of-the-art OCC models learn a compact normality description by hyper-sphere minimisation, but they often suffer from overfitting the training data, especially when the training set is small or contaminated with anomalous samples. To address this issue, we introduce the interpolated Gaussian descriptor (IGD) method, a novel OCC model that learns a one-class Gaussian anomaly classifier trained with adversarially interpolated training samples. The Gaussian anomaly classifier differentiates the training samples based on their distance to the Gaussian centre and the standard deviation of these distances, offering the model a discriminability w.r.t. the given samples during training. The adversarial interpolation is enforced to consistently learn a smooth Gaussian descriptor, even when the training data is small or contaminated with anomalous samples. This enables our model to learn the data description based on the representative normal samples rather than fringe or anomalous samples, resulting in significantly improved normality description. In extensive experiments on diverse popular benchmarks, including MNIST, Fashion MNIST, CIFAR10, MVTec AD and two medical datasets, IGD achieves better detection accuracy than current state-of-the-art models. IGD also shows better robustness in problems with small or contaminated training sets. Code is available at https://github.com/tianyu0207/IGD.

cs.CV↗

arXiv2022

ACPL: Anti-curriculum Pseudo-labelling for Semi-supervised Medical Image Classification

Effective semi-supervised learning (SSL) in medical image analysis (MIA) must address two challenges: 1) work effectively on both multi-class (e.g., lesion classification) and multi-label (e.g., multiple-disease diagnosis) problems, and 2) handle imbalanced learning (because of the high variance in disease prevalence). One strategy to explore in SSL MIA is based on the pseudo labelling strategy, but it has a few shortcomings. Pseudo-labelling has in general lower accuracy than consistency learning, it is not specifically designed for both multi-class and multi-label problems, and it can be challenged by imbalanced learning. In this paper, unlike traditional methods that select confident pseudo label by threshold, we propose a new SSL algorithm, called anti-curriculum pseudo-labelling (ACPL), which introduces novel techniques to select informative unlabelled samples, improving training balance and allowing the model to work for both multi-label and multi-class problems, and to estimate pseudo labels by an accurate ensemble of classifiers (improving pseudo label accuracy). We run extensive experiments to evaluate ACPL on two public medical image classification benchmarks: Chest X-Ray14 for thorax disease multi-label classification and ISIC2018 for skin lesion multi-class classification. Our method outperforms previous SOTA SSL methods on both datasets

cs.CV↗

arXiv2022

Collapsing dust thin shells in Einstein-Gauss-Bonnet gravity

We investigate gravitational collapse of a spherically symmetric thin shell in the Einstein-Gauss-Bonnet (EGB) gravity. Under the recently proposed 4D limit, we find that the collapsing shell will be bounced back at a small radius, without forming a singularity. This bouncing behavior is similar to those of a test particle and a homogeneous spherical dust star, in accordance with the expectation that the Gauss-Bonnet term will modify the small scale behavior of the Einstein gravity. We analyze the causal structure of the dynamic spacetime that represents the bouncing process, finding that the thin shell has an oscillation behavior on the Penrose diagram, which means that the thin shell results in a novel type of black hole with respect to observers outside the event horizon that the collapse forms. We also find that the weak cosmic censorship conjecture holds in this model. Further implications of such a regular gravitational collapse are discussed.

gr-qc↗