相关论文: TinyFormer: Efficient Transformer Design and Deplo…

Many fault diagnosis methods of rotating machines are based on discriminative features extracted from signals collected from the key components such as bearings. However, under complex operating conditions, periodic impulsive…

Limited computational budgets often prevent transformers from being used in production and from having their high accuracy utilized. TinyBERT addresses the computational efficiency by self-distilling BERT into a smaller transformer…

Sparse tensors are prevalent in many data-intensive applications, yet existing differentiable programming frameworks are tailored towards dense tensors. This presents a significant challenge for efficiently computing gradients through…

The trend towards transitioning from monolithic applications to microservices has been widely embraced in modern distributed systems and applications. This shift has resulted in the creation of lightweight, fine-grained, and self-contained…

Enabling efficient and accurate deep neural network (DNN) inference on microcontrollers is non-trivial due to the constrained on-chip resources. Current methodologies primarily focus on compressing larger models yet at the expense of model…

Sparse tensors appear frequently in distributed deep learning, either as a direct artifact of the deep neural network's gradients, or as a result of an explicit sparsification process. Existing communication primitives are agnostic to the…

Tiny machine learning (TinyML) is a rapidly growing field aiming to democratize machine learning (ML) for resource-constrained microcontrollers (MCUs). Given the pervasiveness of these tiny devices, it is inherent to ask whether TinyML…

There is a growing trend to outsource the inference task of large transformer models to cloud servers. However, this poses a severe threat to users' private data as they are exposed to cloud servers after uploading. Although several works…

The recently proposed SparseFormer architecture provides an alternative approach to visual understanding by utilizing a significantly lower number of visual tokens via adjusting RoIs, greatly reducing computational costs while still…

Advancements in computer vision research have put transformer architecture as the state of the art in computer vision tasks. One of the known drawbacks of the transformer architecture is the high number of parameters, this can lead to a…

The deployment of Quantized Neural Networks (QNNs) on resource-constrained edge devices, such as microcontrollers (MCUs), introduces fundamental challenges in balancing model performance, computational complexity, and memory constraints.…

Sparse convolutional neural networks (CNNs) have gained significant traction over the past few years as sparse CNNs can drastically decrease the model size and computations, if exploited befittingly, as compared to their dense counterparts.…

The high demand for computational and storage resources severely impede the deployment of deep convolutional neural networks (CNNs) in limited-resource devices. Recent CNN architectures have proposed reduced complexity versions (e.g.…

Historically, the pursuit of efficient inference has been one of the driving forces behind research into new deep learning architectures and building blocks. Some recent examples include: the squeeze-and-excitation module, depthwise…

In recent years, there has been a significant interest in developing machine learning algorithms on embedded systems. This is particularly relevant for bare metal devices in Internet of Things, Robotics, and Industrial applications that…

Vision Transformers (ViT) have shown their competitive advantages performance-wise compared to convolutional neural networks (CNNs) though they often come with high computational costs. To this end, previous methods explore different…

Although convolutional neural networks (CNNs) have achieved remarkable progress in weakly supervised semantic segmentation (WSSS), the effective receptive field of CNN is insufficient to capture global context information, leading to…

Foundation models for medical imaging demonstrate superior generalization capabilities across diverse anatomical structures and clinical applications. Their outstanding performance relies on substantial computational resources, limiting…

Deploying Vision Transformers on edge devices is challenging due to their high computational complexity, while full offloading to cloud resources presents significant latency overheads. We propose a novel collaborative inference framework,…

On-device training enables the model to adapt to new data collected from the sensors by fine-tuning a pre-trained model. Users can benefit from customized AI models without having to transfer the data to the cloud, protecting the privacy.…