This paper studies a practically meaningful ship detection problem from synthetic aperture radar (SAR) images by neural network. We broadly extract different types of SAR image features and raise the intriguing question if these extracted features are beneficial to (1) suppress data variations (e.g., complex land-sea backgrounds, scattered noise) of real-world SAR images, and (2) enhance the features of ships that are small objects and have different aspect (length-width) ratios, therefore resulting in the improvement of ship detection. To answer this question, we propose a SAR-ship detection neural network (called 3SD-Net for short), by newly developing Bidirectional Coordinate Attention (BCA) and Multi-resolution Feature Fusion (MRF) and a center point distribution module (CPDM) based on CenterNet. In detail, we first develop BCA to make 3SD-Net focus on ship features as much as possible while ignoring the background noise. Second, we leverage MRF to enhance the spatial information of small-scale ships yet solve the non-trivial problem of small-scale and shallower pixels easily lost after deep convolution in SAR images. Moreover, considering the varying length-width ratio of arbitrary ships, we study the probability distribution around the ship center. We concentrate on enhancing the distribution function of the ship center, thereby significantly improving the performance of the basic CenterNet detector. This improvement is achieved without incurring additional computational and time costs. The experimental results obtained from the public SAR-Ship and SSDD datasets demonstrate the superior performance of our method compared to its competitors. Specifically, our 3SD-Net achieves AP values of 91.66% and 90.22% on the two datasets respectively, outperforming YOLOV7 (90.31% and 87.32%) and EfficientVit (90.06% and 90.08%). Source code will be released upon publication .

Data in industrial informatics could be high-dimensional and mislabeled. The irrelevant or noisy features present significant challenges to high-dimensional mislabeled instances detection. Traditional methods often adopt the following method: firstly, searching for the relevant subspace; secondly, using the obtained feature subspace for mislabeled data detection. However, such a two-step method separates the relationship between feature selection and mislabeled detection, which can degrade the mislabeled detection performance. In this paper, we propose a novel sequential ensemble method SENF that aggregates the above two phases. Our method learns the sequential ensembles to obtain a refined feature subspace and improves detection accuracy by iterative sparse modeling with noise scores as the regression target attribute. Through extensive experiments on several real-world high-dimensional datasets, we show that SENF performs significantly better or at least similar to the individual baselines as well as the existing state-of-the-art label noise detection methods.

Data are widely collected via the IoT for machine learning tasks in in-home health monitoring applications and mislabeled training data lead to unreliable machine learning models in in-home health monitoring. Researchers have proposed a wide arrangement of algorithms to deal with mislabeled training data, in which one straightforward and effective solution is to directly filter noise from training data so that the negative effects of mislabeled data can be minimized. In essence, noise filtering might be a suboptimal solution because the mislabeled data are not completely useless. The features and distributions of mislabeled data are still useful for learning, especially when training data are insuffcient. In this work, we propose a novel framework to learn from mislabeled training data through ambiguous learning (LeMAL). LeMAL mainly consists of two parts. First, it converts the original training data to ambiguous data. Second, an ambiguous learning algorithm is applied to the ambiguous data. In this work, we propose a novel distance-based ambiguous learning algorithm so that the ambiguous data can be used in a better way. Finally, we demonstrate that LeMAL can effectively improve learning performance over existing noise filtering methods.