Search Results

News recommendation is an intelligent technology that aims to provide users with matching news content based on their preferences and interests. Nevertheless, current methodologies exhibit significant limitations. Traditional models often rely on ...

Vision Transformer (ViT) has achieved unprecedented success in vision tasks with the assistance of abundant data. However, the lack of inductive bias in lightweight ViT makes learning locality challenging on small datasets, leading to poor ...

• The Lightweight Vision Transformer with knowledge distillation can excel on small datasets.
• Knowledge distillation combined with Curriculum Learning can enhance distillation efficiency.
• Feature-based knowledge distillation can ...

Open-vocabulary object detection aims to train a detector capable of recognizing various novel classes. Most existing studies exploit image-level weak supervision to generate pseudo object boxes for novel class training. However, the generated ...

• Open-vocabulary object detection without using box-annotated images of novel classes.
• Better exploitation of image-level weak supervision for novel class training.
• Proposed debiased curriculum self-training for accurate pseudo-...

Real-time power network dispatching and control (PDC) presents unique challenges that traditional methods cannot effectively address due to the consideration of temporal dynamic factors. Reinforcement learning (RL) has been introduced and proven ...

Accurate depth estimation from monocular images is critical for various applications such as robotics, augmented reality, and autonomous navigation. However, achieving high accuracy while maintaining computational efficiency is a major challenge, ...

Lossy image coding techniques usually result in various undesirable compression artifacts. Recently, deep convolutional neural networks have seen encouraging advances in compression artifact reduction. However, most of them focus on the ...

Portfolio management (PM) is a popular financial process that concerns the occasional reallocation of a particular quantity of capital into a portfolio of assets, with the main aim of maximizing profitability conditioned to a certain level of ...

Sequential recommender systems (SRSs) aim to suggest next item for a user based on her historical interaction sequences. Recently, many research efforts have been devoted to attenuate the influence of noisy items in sequences by either assigning ...

Shadow detection is undergoing a rapid and remarkable development along with the wide use of deep neural networks. Benefiting from a large number of training images annotated with strong pixel-level ground-truth masks, current deep shadow ...

• A novel unsupervised deep shadow detection framework is designed.
• We design an initial pseudo label generation (IPG) module by taking advantages of the complementarity of multiple traditional unsupervised shadow detection models.
• ...

Training models on spatio-temporal (ST) data poses an open problem due to the complicated and diverse nature of the data itself, and it is challenging to ensure the model's performance directly trained on the original ST data. While limiting the variety ...

Universal domain adaptation (UniDA) aims to transfer knowledge between domains without prior knowledge of the label spaces. Category shift and domain shift are two primary challenges in UniDA, which require the method not only to distinguish ...

• The curriculum learning is introduced into universal domain adaptation.
• A curriculum strategy is proposed to solve negative transfer.
• A score mechanism is proposed to detect private samples.
• Graph neural networks are used to ...

Unmanned Aerial Vehicles (UAVs) are increasingly being used for data harvesting from Wireless Sensor Nodes (SNs). This study aims to minimize the Age of Information (AoI) during data collection, while also considering the energy sustainability of ...

• MARL with EPC minimizes AoI effectively.
• EPC algorithm enhances multi-agent learning.
• Energy-efficient trajectories vital for UAV data harvesting.
• AoI minimization constant crucial for real-time tasks.

Adapting large pre-trained foundation models, e.g., SAM, for medical image segmentation remains a significant challenge. A crucial step involves the formulation of a series of specialized prompts that incorporate specific clinical instructions. ...

This study introduces a novel hyperparameter in the Softmax function to regulate the rate of gradient decay, which is dependent on sample probability. Our theoretical and empirical analyses reveal that both model generalization and calibration ...

Contrastive learning is a commonly used framework in the field of graph self-supervised learning, where models are trained by bringing positive samples closer together and pushing negative samples apart. Most existing graph contrastive learning ...

We present a proximal policy optimization agent trained through curriculum learning (CL) principles and meticulous reward engineering to optimize a real-world high-throughput waste sorting facility. Our work addresses the challenge of effectively ...

Traditionally, teaching a human and a Machine Learning (ML) model is quite different, but organized and structured learning has the ability to enable faster and better understanding of the underlying concepts. For example, when humans learn to ...

• Curriculum learning can improve the performance of end-to-end ASR systems.
• A good curriculum strategy can speed up convergence without impacting performance.
• Curriculum learning shows benefits in both low and high resource ...

Knowledge distillation, as a type of model compression algorithms, has been popularly adopted due to its easy implementation and effectiveness. However, transferring knowledge from a teacher network to a student one encounters a bottleneck. ...

Breast lesion segmentation of ultrasound images plays a crucial role in early screening and diagnosis of breast lesions. However, accurately segmenting lesions in breast ultrasound (BUS) images is challenging due to prevalent issues such as low ...

• A region-wise CL is proposed to learn regional features from easy to hard.
• An uncertainty-based regularization method is proposed to separate easy and hard regional features.
• A dynamic fusion method is proposed to dynamically ...

Reinforcement learning (RL) is effective for autonomous navigation tasks without prior knowledge of the environment. However, traditional mobile robot navigation algorithms, based on off-policy RL, often face challenges such as low sample ...

• An end-to-end navigation framework based on off-policy RL is proposed.
• Improving agent learning using a task-level curriculum learning framework.
• Designing a self-paced function to adaptively compute sample prioritization.
• ...