相关论文: IKD+: Reliable Low Complexity Deep Models For Reti…

Knowledge distillation (KD) is a very popular method for model size reduction. Recently, the technique is exploited for quantized deep neural networks (QDNNs) training as a way to restore the performance sacrificed by word-length reduction.…

Deep learning networks are being developed in every stage of the MRI workflow and have provided state-of-the-art results. However, this has come at the cost of increased computation requirement and storage. Hence, replacing the networks…

Deep neural networks (DNNs) have achieved great success in various machine learning tasks. However, most existing powerful DNN models are computationally expensive and memory demanding, hindering their deployment in devices with low memory…

With the improvement of AI chips (e.g., GPU, TPU, and NPU) and the fast development of the Internet of Things (IoT), some robust deep neural networks (DNNs) are usually composed of millions or even hundreds of millions of parameters. Such a…

Deep Neural Networks (DNNs) have achieved notable performance in the fields of computer vision and natural language processing with various applications in both academia and industry. However, with recent advancements in DNNs and…

With the rapid development of artificial intelligence (AI), especially in the medical field, the need for its explainability has grown. In medical image analysis, a high degree of transparency and model interpretability can help clinicians…

Efficient deployment of deep neural networks on resource-constrained devices demands advanced compression techniques that preserve accuracy and interoperability. This paper proposes a machine learning framework that augments Knowledge…

Deep learning models, particularly recurrent neural networks and their variants, such as long short-term memory, have significantly advanced time series data analysis. These models capture complex, sequential patterns in time series,…

Neural network potentials (NNPs) offer a powerful alternative to traditional force fields for molecular dynamics (MD) simulations. Accurate and stable MD simulations, crucial for evaluating material properties, require training data…

Knowledge distillation (KD) enhances the performance of a student network by allowing it to learn the knowledge transferred from a teacher network incrementally. Existing methods dynamically adjust the temperature to enable the student…

Monocular depth estimation (MDE) methods are often either too computationally expensive or not accurate enough due to the trade-off between model complexity and inference performance. In this paper, we propose a lightweight network that can…

Knowledge distillation (KD) is a widely-used technique that utilizes large networks to improve the performance of compact models. Previous KD approaches usually aim to guide the student to mimic the teacher's behavior completely in the…

The human vision and perception system is inherently incremental where new knowledge is continually learned over time whilst existing knowledge is retained. On the other hand, deep learning networks are ill-equipped for incremental…

This study proposes a method for knowledge distillation (KD) of fine-tuned Large Language Models (LLMs) into smaller, more efficient, and accurate neural networks. We specifically target the challenge of deploying these models on…

Deep neural networks have achieved remarkable success in a wide range of practical problems. However, due to the inherent large parameter space, deep models are notoriously prone to overfitting and difficult to be deployed in portable…

DRDr II is a hybrid of machine learning and deep learning worlds. It builds on the successes of its antecedent, namely, DRDr, that was trained to detect, locate, and create segmentation masks for two types of lesions (exudates and…

In existing image classification systems that use deep neural networks, the knowledge needed for image classification is implicitly stored in model parameters. If users want to update this knowledge, then they need to fine-tune the model…

Knowledge Distillation (KD) for object detection aims to train a compact detector by transferring knowledge from a teacher model. Since the teacher model perceives data in a way different from humans, existing KD methods only distill…

In real applications, different computation-resource devices need different-depth networks (e.g., ResNet-18/34/50) with high-accuracy. Usually, existing methods either design multiple networks and train them independently, or construct…

There is a growing discrepancy in computer vision between large-scale models that achieve state-of-the-art performance and models that are affordable in practical applications. In this paper we address this issue and significantly bridge…