Related papers: Early-exit Convolutional Neural Networks
Early-exiting dynamic neural networks (EDNN), as one type of dynamic neural networks, has been widely studied recently. A typical EDNN has multiple prediction heads at different layers of the network backbone. During inference, the model…
Collaborative inference systems are one of the emerging solutions for deploying deep neural networks (DNNs) at the wireless network edge. Their main idea is to divide a DNN into two parts, where the first is shallow enough to be reliably…
We propose Class Based Thresholding (CBT) to reduce the computational cost of early exit semantic segmentation models while preserving the mean intersection over union (mIoU) performance. A key idea of CBT is to exploit the…
While the Internet of Things (IoT) technology is booming and offers huge opportunities for information exchange, it also faces unprecedented security challenges. As an important complement to the physical layer security technologies for…
Deep neural network (DNN) models are increasingly popular in edge video analytic applications. However, the compute-intensive nature of DNN models pose challenges for energy-efficient inference on resource-constrained edge devices. Most…
Seizure prediction has attracted a growing attention as one of the most challenging predictive data analysis efforts in order to improve the life of patients living with drug-resistant epilepsy and tonic seizures. Many outstanding works…
Early-exit deep neural networks enable adaptive inference by terminating computation when sufficient confidence is achieved, reducing cost for edge AI accelerators in resource-constrained settings. Existing methods, however, rely on…
Parameter-efficient transfer learning (PETL) has shown great potential in adapting a vision transformer (ViT) pre-trained on large-scale datasets to various downstream tasks. Existing studies primarily focus on minimizing the number of…
Recent ensemble learning methods for image classification have been shown to improve classification accuracy with low extra cost. However, they still require multiple trained models for ensemble inference, which eventually becomes a…
As traditional neural network consumes a significant amount of computing resources during back propagation, \citet{Sun2017mePropSB} propose a simple yet effective technique to alleviate this problem. In this technique, only a small subset…
Deep learning models that perform well often have high computational costs. In this paper, we combine two approaches that try to reduce the computational cost while keeping the model performance high: pruning and early exit networks. We…
The Internet of Things is transforming various fields, with sensors increasingly embedded in wearables, smart buildings, and connected equipment. While deep learning enables valuable insights from IoT data, conventional models are too…
Deep neural networks provide state-of-the-art accuracy for vision tasks but they require significant resources for training. Thus, they are trained on cloud servers far from the edge devices that acquire the data. This issue increases…
Convolutional Neural Networks (CNNs) have demonstrated remarkable ability throughout the field of computer vision. However, CNN inference requires a large number of arithmetic operations, making them expensive to deploy in hardware. Current…
Deep neural networks (DNNs) have made significant progress in recognizing visual elements and generating descriptive text in image-captioning tasks. However, their improved performance comes from increased computational burden and inference…
Deploying large language model inference remains challenging due to their high computational overhead. Early exit optimizes model inference by adaptively reducing the number of inference layers. Current methods typically train internal…
Convolutional neural networks (CNNs) demand huge DRAM bandwidth for computational imaging tasks, and block-based processing has recently been applied to greatly reduce the bandwidth. However, the induced additional computation for feature…
Reducing computational costs is an important issue for development of embedded systems. Binary-weight Neural Networks (BNNs), in which weights are binarized and activations are quantized, are employed to reduce computational costs of…
Ensemble methods can deliver surprising performance gains but also bring significantly higher computational costs, e.g., can be up to 2048X in large-scale ensemble tasks. However, we found that the majority of computations in ensemble…
Deployment of dynamic neural networks on edge accelerators requires careful consideration of hardware constraints beyond conventional complexity metrics such as Multiply-Accumulate operations. In Early-Exiting Neural Networks (EENN), exit…