Related papers: An Iteratively Optimized Patch Label Inference Net…

Detecting lane lines from sensors is becoming an increasingly significant part of autonomous driving systems. However, less development has been made on high-definition lane-level mapping based on aerial images, which could automatically…

This work proposes PatchNet, an automated tool based on hierarchical deep learning for classifying patches by extracting features from commit messages and code changes. PatchNet contains a deep hierarchical structure that mirrors the…

Detecting a specific horizon in seismic images is a valuable tool for geological interpretation. Because hand-picking the locations of the horizon is a time-consuming process, automated computational methods were developed starting three…

Deep neural networks (DNNs) are one of the most widely used machine learning algorithm. DNNs requires the training data to be available beforehand with true labels. This is not feasible for many real-world problems where data arrives in the…

Deep learning (DL) has demonstrated its powerful capabilities in the field of image inpainting, which could produce visually plausible results. Meanwhile, the malicious use of advanced image inpainting tools (e.g. removing key objects to…

Frequently recurring transient faults in a transmission network may be indicative of impending permanent failures. Hence, determining their location is a critical task. This paper proposes a novel image embedding aided deep learning…

Recently, there has been an impetus for the application of cutting-edge data collection platforms such as drones mounted with camera sensors for infrastructure asset management. However, the sensor characteristics, proximity to the…

Physics-informed neural networks (PINNs) formulate the solution of partial differential equations as residual minimization problems over neural network parameterizations. Although highly flexible, optimization of PINNs using modern variants…

Autonomous vehicle perception systems require robust pedestrian detection, particularly on geometrically complex roadways like Type-S curved surfaces, where standard RGB camera-based methods face limitations. This paper introduces YOLO-APD,…

Patch-level image representation is very important for object classification and detection, since it is robust to spatial transformation, scale variation, and cluttered background. Many existing methods usually require fine-grained…

Accurate detection of nutrient deficiency in plant leaves is essential for precision agriculture, enabling early intervention in fertilization, disease, and stress management. This study presents a deep learning framework for leaf anomaly…

Machine learning classification systems are susceptible to poor performance when trained with incorrect ground truth labels, even when data is well-curated by expert annotators. As machine learning becomes more widespread, it is…

A neural network targeting at unsupervised image anomaly localization, called the PEDENet, is proposed in this work. PEDENet contains a patch embedding (PE) network, a density estimation (DE) network, and an auxiliary network called the…

Software systems increasingly include AI components based on deep learning (DL). Reliable testing of such systems requires near-perfect test-input validity and label accuracy, with minimal human effort. Yet, the DL community has largely…

We present CoopNet, an approach that improves the cooperation of co-trained networks by dynamically adapting the apportionment of gradient, to ensure equitable learning progress. It is applied to motion-aware self-supervised prediction of…

Based on multiple instance detection networks (MIDN), plenty of works have contributed tremendous efforts to weakly supervised object detection (WSOD). However, most methods neglect the fact that the overwhelming negative instances exist in…

Deep learning has achieved excellent performance in various computer vision tasks, but requires a lot of training examples with clean labels. It is easy to collect a dataset with noisy labels, but such noise makes networks overfit seriously…

Spatial downsampling layers are favored in convolutional neural networks (CNNs) to downscale feature maps for larger receptive fields and less memory consumption. However, for discriminative tasks, there is a possibility that these layers…

Unsupervised domain adaptation(UDA) has been applied to image semantic segmentation to solve the problem of domain offset. However, in some difficult categories with poor recognition accuracy, the segmentation effects are still not ideal.…

Predicting fracture load in laminated composites with stress raisers is challenging due to complex failure mechanisms such as delamination, fibre breakage, and matrix cracking, which are heavily influenced by fibre orientation, layup…