A new learning paradigm, self-supervised learning (SSL), can be used to solve such problems by pre-training a general model with large unlabeled images and then fine-tuning on a downstream task with very few labeled samples. Contrastive learning is a typical method of SSL, which can learn general invariant features. However, most of the existing contrastive learning is designed for classification tasks to obtain an image-level representation, which may be sub-optimal for semantic segmentation tasks requiring pixel-level discrimination. Therefore, we propose Global style and Local matching Contrastive Learning Network (GLCNet) for remote sensing semantic segmentation. Specifically, the global style contrastive module is used to learn an image-level representation better, as we consider the style features can better represent the overall image features; The local features matching contrastive module is designed to learn representations of local regions which is beneficial for semantic segmentation. We evaluate four remote sensing semantic segmentation datasets, and the experimental results show that our method mostly outperforms state-of-the-art self-supervised methods and ImageNet pre-training. Specifically, with 1\% annotation from the original dataset, our approach improves Kappa by 6\% on the ISPRS Potsdam dataset and 3\% on Deep Globe Land Cover Classification dataset relative to the existing baseline. Moreover, our method outperforms supervised learning when there are some differences between the datasets of upstream tasks and downstream tasks. Our study promotes the development of self-supervised learning in the field of remote sensing semantic segmentation. The source code is available at https://github.com/GeoX-Lab/G-RSIM.
Background: Extensive clinical evidence suggests that a preventive screening of coronary heart disease (CHD) at an earlier stage can greatly reduce the mortality rate. We use 64 two-dimensional speckle tracking echocardiography (2D-STE) features and seven clinical features to predict whether one has CHD. Methods: We develop a machine learning approach that integrates a number of popular classification methods together by model stacking, and generalize the traditional stacking method to a two-step stacking method to improve the diagnostic performance. Results: By borrowing strengths from multiple classification models through the proposed method, we improve the CHD classification accuracy from around 70% to 87.7% on the testing set. The sensitivity of the proposed method is 0.903 and the specificity is 0.843, with an AUC of 0.904, which is significantly higher than those of the individual classification models. Conclusions: Our work lays a foundation for the deployment of speckle tracking echocardiography-based screening tools for coronary heart disease.
Feature alignment between domains is one of the mainstream methods for Unsupervised Domain Adaptation (UDA) semantic segmentation. Existing feature alignment methods for semantic segmentation learn domain-invariant features by adversarial training to reduce domain discrepancy, but they have two limits: 1) associations among pixels are not maintained, 2) the classifier trained on the source domain couldn't adapted well to the target. In this paper, we propose a new UDA semantic segmentation approach based on domain closeness assumption to alleviate the above problems. Specifically, a prototype clustering strategy is applied to cluster pixels with the same semantic, which will better maintain associations among target domain pixels during the feature alignment. After clustering, to make the classifier more adaptive, a normalized cut loss based on the affinity graph of the target domain is utilized, which will make the decision boundary target-specific. Sufficient experiments conducted on GTA5 $\rightarrow$ Cityscapes and SYNTHIA $\rightarrow$ Cityscapes proved the effectiveness of our method, which illustrated that our results achieved the new state-of-the-art.
Sketching is a dimensionality reduction technique where one compresses a matrix by linear combinations that are typically chosen at random. A line of work has shown how to sketch the Hessian to speed up each iteration in a second order method, but such sketches usually depend only on the matrix at hand, and in a number of cases are even oblivious to the input matrix. One could instead hope to learn a distribution on sketching matrices that is optimized for the specific distribution of input matrices. We show how to design learned sketches for the Hessian in the context of second order methods, where we learn potentially different sketches for the different iterations of an optimization procedure. We show empirically that learned sketches, compared with their "non-learned" counterparts, improve the approximation accuracy for important problems, including LASSO, SVM, and matrix estimation with nuclear norm constraints. Several of our schemes can be proven to perform no worse than their unlearned counterparts. Additionally, we show that a smaller sketching dimension of the column space of a tall matrix is possible, assuming an oracle for predicting rows which have a large leverage score.
This paper presents the development of machine learning-enabled data-driven models for effective capacity predictions for lithium-ion batteries under different cyclic conditions. To achieve this, a model structure is first proposed with the considerations of battery ageing tendency and the corresponding operational temperature and depth-of-discharge. Then based on a systematic understanding of covariance functions within the Gaussian process regression, two related data-driven models are developed. Specifically, by modifying the isotropic squared exponential kernel with an automatic relevance determination structure, 'Model A' could extract the highly relevant input features for capacity predictions. Through coupling the Arrhenius law and a polynomial equation into a compositional kernel, 'Model B' is capable of considering the electrochemical and empirical knowledge of battery degradation. The developed models are validated and compared on the Nickel Manganese Cobalt Oxide (NMC) lithium-ion batteries with various cycling patterns. Experimental results demonstrate that the modified Gaussian process regression model considering the battery electrochemical and empirical ageing signature outperforms other counterparts and is able to achieve satisfactory results for both one-step and multi-step predictions. The proposed technique is promising for battery capacity predictions under various cycling cases.
We propose a new task named Audio-driven Per-formance Video Generation (APVG), which aims to synthesizethe video of a person playing a certain instrument guided bya given music audio clip. It is a challenging task to gener-ate the high-dimensional temporal consistent videos from low-dimensional audio modality. In this paper, we propose a multi-staged framework to achieve this new task to generate realisticand synchronized performance video from given music. Firstly,we provide both global appearance and local spatial informationby generating the coarse videos and keypoints of body and handsfrom a given music respectively. Then, we propose to transformthe generated keypoints to heatmap via a differentiable spacetransformer, since the heatmap offers more spatial informationbut is harder to generate directly from audio. Finally, wepropose a Structured Temporal UNet (STU) to extract bothintra-frame structured information and inter-frame temporalconsistency. They are obtained via graph-based structure module,and CNN-GRU based high-level temporal module respectively forfinal video generation. Comprehensive experiments validate theeffectiveness of our proposed framework.
We introduce a novel self-supervised pretext task for learning representations from audio-visual content. Prior work on audio-visual representation learning leverages correspondences at the video level. Approaches based on audio-visual correspondence (AVC) predict whether audio and video clips originate from the same or different video instances. Audio-visual temporal synchronization (AVTS) further discriminates negative pairs originated from the same video instance but at different moments in time. While these approaches learn high-quality representations for downstream tasks such as action recognition, their training objectives disregard spatial cues naturally occurring in audio and visual signals. To learn from these spatial cues, we tasked a network to perform contrastive audio-visual spatial alignment of 360{\deg} video and spatial audio. The ability to perform spatial alignment is enhanced by reasoning over the full spatial content of the 360{\deg} video using a transformer architecture to combine representations from multiple viewpoints. The advantages of the proposed pretext task are demonstrated on a variety of audio and visual downstream tasks, including audio-visual correspondence, spatial alignment, action recognition, and video semantic segmentation.
In a modern vehicle, there are over seventy Electronics Control Units (ECUs). For an in-vehicle network, ECUs communicate with each other by following a standard communication protocol, such as Controller Area Network (CAN). However, an attacker can easily access the in-vehicle network to compromise ECUs through a WLAN or Bluetooth. Though there are various deep learning (DL) methods suggested for securing in-vehicle networks, recent studies on adversarial examples have shown that attackers can easily fool DL models. In this research, we further explore adversarial examples in an in-vehicle network. We first discover and implement two adversarial attack models that are harmful to a Long Short Term Memory (LSTM)-based detection model used in the in-vehicle network. Then, we propose an Adversarial Attack Defending System (AADS) for securing an in-vehicle network. Specifically, we focus on brake-related ECUs in an in-vehicle network. Our experimental results demonstrate that adversaries can easily attack the LSTM-based detection model with a success rate of over 98%, and the proposed AADS achieves over 99% accuracy for detecting adversarial attacks.
We study the space complexity of solving the bias-regularized SVM problem in the streaming model. This is a classic supervised learning problem that has drawn lots of attention, including for developing fast algorithms for solving the problem approximately. One of the most widely used algorithms for approximately optimizing the SVM objective is Stochastic Gradient Descent (SGD), which requires only $O(\frac{1}{\lambda\epsilon})$ random samples, and which immediately yields a streaming algorithm that uses $O(\frac{d}{\lambda\epsilon})$ space. For related problems, better streaming algorithms are only known for smooth functions, unlike the SVM objective that we focus on in this work. We initiate an investigation of the space complexity for both finding an approximate optimum of this objective, and for the related ``point estimation'' problem of sketching the data set to evaluate the function value $F_\lambda$ on any query $(\theta, b)$. We show that, for both problems, for dimensions $d=1,2$, one can obtain streaming algorithms with space polynomially smaller than $\frac{1}{\lambda\epsilon}$, which is the complexity of SGD for strongly convex functions like the bias-regularized SVM, and which is known to be tight in general, even for $d=1$. We also prove polynomial lower bounds for both point estimation and optimization. In particular, for point estimation we obtain a tight bound of $\Theta(1/\sqrt{\epsilon})$ for $d=1$ and a nearly tight lower bound of $\widetilde{\Omega}(d/{\epsilon}^2)$ for $d = \Omega( \log(1/\epsilon))$. Finally, for optimization, we prove a $\Omega(1/\sqrt{\epsilon})$ lower bound for $d = \Omega( \log(1/\epsilon))$, and show similar bounds when $d$ is constant.