Related papers: Multi-Mode Inference Engine for Convolutional Neur…
Camera model identification (CMI) has gained significant importance in image forensics as digitally altered images are becoming increasingly commonplace. In this paper, a novel convolutional neural network (CNN) architecture is proposed for…
Convolution neural network (CNN), as one of the most powerful and popular technologies, has achieved remarkable progress for image and video classification since its invention in 1989. However, with the high definition video-data explosion,…
Large-scale convolutional neural networks (CNNs) suffer from very long training times, spanning from hours to weeks, limiting the productivity and experimentation of deep learning practitioners. As networks grow in size and complexity,…
Existing approaches to improve the performances of convolutional neural networks by optimizing the local architectures or deepening the networks tend to increase the size of models significantly. In order to deploy and apply the neural…
While recent advances in deep learning have led to significant improvements in facial expression classification (FEC), a major challenge that remains a bottleneck for the widespread deployment of such systems is their high architectural and…
There is an increasing interest in applying deep learning to 3D mesh segmentation. We observe that 1) existing feature-based techniques are often slow or sensitive to feature resizing, 2) there are minimal comparative studies and 3)…
Deep convolutional neural networks (CNNs) have made impressive progress in many video recognition tasks such as video pose estimation and video object detection. However, CNN inference on video is computationally expensive due to processing…
Graph neural networks (GNN) analysis engines are vital for real-world problems that use large graph models. Challenges for a GNN hardware platform include the ability to (a) host a variety of GNNs, (b) handle high sparsity in input vertex…
Unleashing the full potential of massive MIMO in FDD mode by reducing the overhead of CSI feedback has recently garnered attention. Numerous deep learning for massive MIMO CSI feedback approaches have demonstrated their efficiency and…
We focus on computation offloading of applications based on convolutional neural network (CNN) from moving devices, such as mobile robots or autonomous vehicles, to MultiAccess Edge Computing (MEC) servers via a mobile network. In order to…
Mixture-of-Experts (MoE) model architectures can significantly reduce the number of activated parameters per token, enabling computationally efficient training and inference. However, their large overall parameter counts and model sizes…
Convolutional Neural Networks (CNNs) have emerged as a fundamental technology for machine learning. High performance and extreme energy efficiency are critical for deployments of CNNs in a wide range of situations, especially mobile…
Major winning Convolutional Neural Networks (CNNs), such as VGGNet, ResNet, DenseNet, \etc, include tens to hundreds of millions of parameters, which impose considerable computation and memory overheads. This limits their practical usage in…
Conventionally, spatiotemporal modeling network and its complexity are the two most concentrated research topics in video action recognition. Existing state-of-the-art methods have achieved excellent accuracy regardless of the complexity…
This work evaluates State-of-the-Art convolution algorithms for CPU-based CNN inference. Although most prior studies focus on GPUs or NPUs, CPU implementations remain comparatively under-optimized. Our first contribution is to provide fair…
Mixture of Experts (MoE) LLMs, characterized by their sparse activation patterns, offer a promising approach to scaling language models while avoiding proportionally increasing the inference cost. However, their large parameter sizes…
Convolutional neural networks (CNN) are widely used in computer vision, especially in image classification. However, the way in which information and invariance properties are encoded through in deep CNN architectures is still an open…
In recent years, convolutional neural network has gained popularity in many engineering applications especially for computer vision. In order to achieve better performance, often more complex structures and advanced operations are…
1D-CNNs are used for time series classification in various domains with a high degree of accuracy. Most implementations collect the incoming data samples in a buffer before performing inference on it. On edge devices, which are typically…
After the tremendous success of convolutional neural networks in image classification, object detection, speech recognition, etc., there is now rising demand for deployment of these compute-intensive ML models on tightly power constrained…