Vehicle detection accuracy is fairly accurate in good-illumination conditions but susceptible to poor detection accuracy under low-light conditions. The combined effect of low-light and glare from vehicle headlight or tail-light results in misses in vehicle detection more likely by state-of-the-art object detection models. However, thermal infrared images are robust to illumination changes and are based on thermal radiations. Recently, Generative Adversarial Networks (GANs) have been extensively used in image domain transfer tasks. State-of-the-art GAN models have attempted to improve vehicle detection accuracy in night-time by converting infrared images to day-time RGB images. However, these models have been found to under-perform during night-time conditions compared to day-time conditions. Therefore, this study attempts to alleviate this shortcoming by proposing three different approaches based on combination of GAN models at two different levels that tries to reduce the feature distribution gap between day-time and night-time infrared images. Quantitative analysis to compare the performance of the proposed models with the state-of-the-art models have been done by testing the models using state-of-the-art object detection models. Both the quantitative and qualitative analyses have shown that the proposed models outperform the state-of-the-art GAN models for vehicle detection in night-time conditions, showing the efficacy of the proposed models.
Training robust speaker verification systems without speaker labels has long been a challenging task. Previous studies observed a large performance gap between self-supervised and fully supervised methods. In this paper, we apply a non-contrastive self-supervised learning framework called DIstillation with NO labels (DINO) and propose two regularization terms applied to embeddings in DINO. One regularization term guarantees the diversity of the embeddings, while the other regularization term decorrelates the variables of each embedding. The effectiveness of various data augmentation techniques are explored, on both time and frequency domain. A range of experiments conducted on the VoxCeleb datasets demonstrate the superiority of the regularized DINO framework in speaker verification. Our method achieves the state-of-the-art speaker verification performance under a single-stage self-supervised setting on VoxCeleb. The codes will be made publicly-available.
In this article, we evaluate unsupervised anomaly detection methods in multispectral images obtained with a wavelength-independent synthetic aperture sensing technique, called Airborne Optical Sectioning (AOS). With a focus on search and rescue missions that apply drones to locate missing or injured persons in dense forest and require real-time operation, we evaluate runtime vs. quality of these methods. Furthermore, we show that color anomaly detection methods that normally operate in the visual range always benefit from an additional far infrared (thermal) channel. We also show that, even without additional thermal bands, the choice of color space in the visual range already has an impact on the detection results. Color spaces like HSV and HLS have the potential to outperform the widely used RGB color space, especially when color anomaly detection is used for forest-like environments.
We study the regret guarantee for risk-sensitive reinforcement learning (RSRL) via distributional reinforcement learning (DRL) methods. In particular, we consider finite episodic Markov decision processes whose objective is the entropic risk measure (EntRM) of return. We identify a key property of the EntRM, the monotonicity-preserving property, which enables the risk-sensitive distributional dynamic programming framework. We then propose two novel DRL algorithms that implement optimism through two different schemes, including a model-free one and a model-based one. We prove that both of them attain $\tilde{\mathcal{O}}(\frac{\exp(|\beta| H)-1}{|\beta|H}H\sqrt{HS^2AT})$ regret upper bound, where $S$ is the number of states, $A$ the number of states, $H$ the time horizon and $T$ the number of total time steps. It matches RSVI2 proposed in \cite{fei2021exponential} with a much simpler regret analysis. To the best of our knowledge, this is the first regret analysis of DRL, which bridges DRL and RSRL in terms of sample complexity. Finally, we improve the existing lower bound by proving a tighter bound of $\Omega(\frac{\exp(\beta H/6)-1}{\beta H}H\sqrt{SAT})$ for $\beta>0$ case, which recovers the tight lower bound $\Omega(H\sqrt{SAT})$ in the risk-neutral setting.
This work describes the development and validation of a fully automated deep learning model, iDAScore v2.0, for the evaluation of embryos incubated for 2, 3, and 5 or more days. The model is trained and evaluated on an extensive and diverse dataset including 181,428 embryos from 22 IVF clinics across the world. For discriminating transferred embryos with known outcome (KID), we show AUCs ranging from 0.621 to 0.708 depending on the day of transfer. Predictive performance increased over time and showed a strong correlation with morphokinetic parameters. The model has equivalent performance to KIDScore D3 on day 3 embryos while significantly surpassing the performance of KIDScore D5 v3 on day 5+ embryos. This model provides an analysis of time-lapse sequences without the need for user input, and provides a reliable method for ranking embryos for likelihood to implant, at both cleavage and blastocyst stages. This greatly improves embryo grading consistency and saves time compared to traditional embryo evaluation methods.
The impact performance of the wheel during wheel development must be ensured through a wheel impact test for vehicle safety. However, manufacturing and testing a real wheel take a significant amount of time and money because developing an optimal wheel design requires numerous iterative processes of modifying the wheel design and verifying the safety performance. Accordingly, the actual wheel impact test has been replaced by computer simulations, such as Finite Element Analysis (FEA), but it still requires high computational costs for modeling and analysis. Moreover, FEA experts are needed. This study presents an aluminum road wheel impact performance prediction model based on deep learning that replaces the computationally expensive and time-consuming 3D FEA. For this purpose, 2D disk-view wheel image data, 3D wheel voxel data, and barrier mass value used for wheel impact test are utilized as the inputs to predict the magnitude of maximum von Mises stress, corresponding location, and the stress distribution of 2D disk-view. The wheel impact performance prediction model can replace the impact test in the early wheel development stage by predicting the impact performance in real time and can be used without domain knowledge. The time required for the wheel development process can be shortened through this mechanism.
Edge intelligence autonomous driving (EIAD) offers computing resources in autonomous vehicles for training deep neural networks. However, wireless channels between the edge server and autonomous vehicles are time-varying due to the high-mobility of vehicles. Moreover, the required number of training samples for different data modalities (e.g., images, point-clouds) is diverse. Consequently, when collecting these datasets from vehicles to the edge server, the associated bandwidth and power allocation across all data frames is a large-scale multi-modal optimization problem. This article proposes a highly computationally efficient algorithm that directly maximizes the quality of training (QoT). The key ingredients include a data-driven model for quantifying the priority of data modality and two first-order methods termed accelerated gradient projection and dual decomposition for low-complexity resource allocation. High-fidelity simulations in Car Learning to Act (CARLA) show that the proposed algorithm reduces the perception error by $3\%$ and the computation time by $98\%$.
Regime shifts in high-dimensional time series arise naturally in many applications, from neuroimaging to finance. This problem has received considerable attention in low-dimensional settings, with both Bayesian and frequentist methods used extensively for parameter estimation. The EM algorithm is a particularly popular strategy for parameter estimation in low-dimensional settings, although the statistical properties of the resulting estimates have not been well understood. Furthermore, its extension to high-dimensional time series has proved challenging. To overcome these challenges, in this paper we propose an approximate EM algorithm for Markov-switching VAR models that leads to efficient computation and also facilitates the investigation of asymptotic properties of the resulting parameter estimates. We establish the consistency of the proposed EM algorithm in high dimensions and investigate its performance via simulation studies.
Detecting anomalies in multivariate time-series data is essential in many real-world applications. Recently, various deep learning-based approaches have shown considerable improvements in time-series anomaly detection. However, existing methods still have several limitations, such as long training time due to their complex model designs or costly tuning procedures to find optimal hyperparameters (e.g., sliding window length) for a given dataset. In our paper, we propose a novel method called Implicit Neural Representation-based Anomaly Detection (INRAD). Specifically, we train a simple multi-layer perceptron that takes time as input and outputs corresponding values at that time. Then we utilize the representation error as an anomaly score for detecting anomalies. Experiments on five real-world datasets demonstrate that our proposed method outperforms other state-of-the-art methods in performance, training speed, and robustness.
Change detection (CD) is to decouple object changes (i.e., object missing or appearing) from background changes (i.e., environment variations) like light and season variations in two images captured in the same scene over a long time span, presenting critical applications in disaster management, urban development, etc. In particular, the endless patterns of background changes require detectors to have a high generalization against unseen environment variations, making this task significantly challenging. Recent deep learning-based methods develop novel network architectures or optimization strategies with paired-training examples, which do not handle the generalization issue explicitly and require huge manual pixel-level annotation efforts. In this work, for the first attempt in the CD community, we study the generalization issue of CD from the perspective of data augmentation and develop a novel weakly supervised training algorithm that only needs image-level labels. Different from general augmentation techniques for classification, we propose the background-mixed augmentation that is specifically designed for change detection by augmenting examples under the guidance of a set of background changing images and letting deep CD models see diverse environment variations. Moreover, we propose the augmented & real data consistency loss that encourages the generalization increase significantly. Our method as a general framework can enhance a wide range of existing deep learning-based detectors. We conduct extensive experiments in two public datasets and enhance four state-of-the-art methods, demonstrating the advantages of