Related papers: FPN-fusion: Enhanced Linear Complexity Time Series…

Traffic flow forecasting is challenging due to the intricate spatio-temporal correlations in traffic flow data. Existing Transformer-based methods usually treat traffic flow forecasting as multivariate time series (MTS) forecasting.…

Considering the models that apply the contextual information of time-series data could improve the fault diagnosis performance, some neural network structures such as RNN, LSTM, and GRU were proposed to model the fault diagnosis…

In this paper, we present an efficient pedestrian detection system, designed by fusion of multiple deep neural network (DNN) systems. Pedestrian candidates are first generated by a single shot convolutional multi-box detector at different…

Fault detection in rotating machinery is a complex task, particularly in small and heterogeneous dataset scenarios. Variability in sensor placement, machinery configurations, and structural differences further increase the complexity of the…

Weather forecasting remains a crucial yet challenging domain, where recently developed models based on deep learning (DL) have approached the performance of traditional numerical weather prediction (NWP) models. However, these DL models,…

While numerous forecasters have been proposed using different network architectures, the Transformer-based models have state-of-the-art performance in time series forecasting. However, forecasters based on Transformers are still suffering…

Generative modeling has recently undergone remarkable advancements, primarily propelled by the transformative implications of Diffusion Probabilistic Models (DPMs). The impressive capability of these models, however, often entails…

Time series anomaly detection is a pivotal task in data analysis, yet it poses the challenge of discerning normal and abnormal patterns in label-deficient scenarios. While prior studies have largely employed reconstruction-based approaches,…

Learning curve extrapolation aims to predict model performance in later epochs of training, based on the performance in earlier epochs. In this work, we argue that, while the inherent uncertainty in the extrapolation of learning curves…

The vast majority of time-series forecasting approaches require a substantial training dataset. However, many real-life forecasting applications have very little initial observations, sometimes just 40 or fewer. Thus, the applicability of…

Off-the-shelf machine learning algorithms for prediction such as regularized logistic regression cannot exploit the information of time-varying features without previously using an aggregation procedure of such sequential data. However,…

Many real-world datasets are time series that are sequentially collected and contain rich temporal information. Thus, a common interest in practice is to capture dynamics of time series and predict their future evolutions. To this end, the…

Deep Convolutional Neural Networks~(CNNs) offer remarkable performance of classifications and regressions in many high-dimensional problems and have been widely utilized in real-word cognitive applications. However, high computational cost…

Current approaches for time series forecasting, whether in the time or frequency domain, predominantly use deep learning models based on linear layers or transformers. They often encode time series data in a black-box manner and rely on…

The recent success of Deep Neural Networks (DNNs) has drastically improved the state of the art for many application domains. While achieving high accuracy performance, deploying state-of-the-art DNNs is a challenge since they typically…

Time series forecasting is essential for many practical applications, with the adoption of transformer-based models on the rise due to their impressive performance in NLP and CV. Transformers' key feature, the attention mechanism,…

Federated learning (FL) facilitates the secure utilization of decentralized images, advancing applications in medical image recognition and autonomous driving. However, conventional FL faces two critical challenges in real-world deployment:…

Recent progress in foundation models has enabled strong zero-shot performance for time series forecasting. In this work, we show that such capabilities can also emerge from tabular foundation models. We introduce TabPFN-TS, a simple method…

Feature pyramid network (FPN) based models, which fuse the semantics and salient details in a progressive manner, have been proven highly effective in salient object detection. However, it is observed that these models often generate…

To build light-weight network, we propose a new normalization, Fine-grained Batch Normalization (FBN). Different from Batch Normalization (BN), which normalizes the final summation of the weighted inputs, FBN normalizes the intermediate…