Related papers: FastCAR: Fast Classification And Regression for Ta…
Multi-task learning (MTL) is a powerful approach in deep learning that leverages the information from multiple tasks during training to improve model performance. In medical imaging, MTL has shown great potential to solve various tasks.…
Autoregressive networks can achieve promising performance in many sequence modeling tasks with short-range dependence. However, when handling high-dimensional inputs and outputs, the huge amount of parameters in the network lead to…
The effectiveness of contrastive learning technology in natural language processing tasks is yet to be explored and analyzed. How to construct positive and negative samples correctly and reasonably is the core challenge of contrastive…
Recent studies have revealed that, beyond conventional accuracy, calibration should also be considered for training modern deep neural networks. To address miscalibration during learning, some methods have explored different penalty…
Recent work done on lane detection has been able to detect lanes accurately in complex scenarios, yet many fail to deliver real-time performance specifically with limited computational resources. In this work, we propose SwiftLane: a simple…
Vehicle detection in real-time scenarios is challenging because of the time constraints and the presence of multiple types of vehicles with different speeds, shapes, structures, etc. This paper presents a new method relied on generating a…
We present a novel deep neural model for text detection in document images. For robust text detection in noisy scanned documents, the advantages of multi-task learning are adopted by adding an auxiliary task of text enhancement. Namely, our…
In this paper, we introduce a Fast and Scalable Semi-supervised Multi-view Subspace Clustering (FSSMSC) method, a novel solution to the high computational complexity commonly found in existing approaches. FSSMSC features linear…
Object segmentation is a key component in the visual system of a robot that performs tasks like grasping and object manipulation, especially in presence of occlusions. Like many other computer vision tasks, the adoption of deep…
Graph Neural Networks (GNNs) have shown great superiority on non-Euclidean graph data, achieving ground-breaking performance on various graph-related tasks. As a practical solution to train GNN on large graphs with billions of nodes and…
Spatio-temporal machine learning is critically needed for a variety of societal applications, such as agricultural monitoring, hydrological forecast, and traffic management. These applications greatly rely on regional features that…
The Multi-Task Learning (MTL) technique has been widely studied by word-wide researchers. The majority of current MTL studies adopt the hard parameter sharing structure, where hard layers tend to learn general representations over all tasks…
Representation learning of the task-oriented attention while tracking instrument holds vast potential in image-guided robotic surgery. Incorporating cognitive ability to automate the camera control enables the surgeon to concentrate more on…
Meta-learning is widely used in few-shot classification and function regression due to its ability to quickly adapt to unseen tasks. However, it has not yet been well explored on regression tasks with high dimensional inputs such as images.…
Supervised learning has been widely used for attack categorization, requiring high-quality data and labels. However, the data is often imbalanced and it is difficult to obtain sufficient annotations. Moreover, supervised models are subject…
Bearing fault diagnosis in rotating machinery is critical for ensuring operational reliability, therefore early fault detection is essential to avoid catastrophic failures and expensive emergency repairs. Traditional methods like Fast…
This paper discusses a system that accelerates reinforcement learning by using transfer from related tasks. Without such transfer, even if two tasks are very similar at some abstract level, an extensive re-learning effort is required. The…
Object detection has been one of the most active topics in computer vision for the past years. Recent works have mainly focused on pushing the state-of-the-art in the general-purpose COCO benchmark. However, the use of such detection…
Recent segmentation methods, such as OCR and CPNet, utilizing "class level" information in addition to pixel features, have achieved notable success for boosting the accuracy of existing network modules. However, the extracted class-level…
Multi-task learning (MTL) in materials science relies on the assumption that physically related properties share learnable representations. We challenge this assumption using a 54,028-sample metal alloy dataset exhibiting extreme task-level…