Related papers: PICO: Pipeline Inference Framework for Versatile C…

Feature pyramids have been proven powerful in image understanding tasks that require multi-scale features. State-of-the-art methods for multi-scale feature learning focus on performing feature interactions across space and scales using…

In this paper, we describe a novel deep convolutional neural network (CNN) that is deeper and wider than other existing deep networks for hyperspectral image classification. Unlike current state-of-the-art approaches in CNN-based…

In this paper, we present a conceptually simple, strong, and efficient framework for panoptic segmentation, called Panoptic FCN. Our approach aims to represent and predict foreground things and background stuff in a unified fully…

Deep Neural Networks (DNNs) are increasingly deployed across diverse industries, driving demand for mobile device support. However, existing mobile inference frameworks often rely on a single processor per model, limiting hardware…

Deep neural networks (DNNs) are ubiquitous in computer vision and natural language processing, but suffer from high inference cost. This problem can be addressed by quantization, which consists in converting floating point perations into a…

Graph Neural Networks (GNNs) are powerful tools for learning graph-structured data, but their scalability is hindered by inefficient mini-batch generation, data transfer bottlenecks, and costly inter-GPU synchronization. Existing training…

The Pachinko Allocation Machine (PAM) is a deep topic model that allows representing rich correlation structures among topics by a directed acyclic graph over topics. Because of the flexibility of the model, however, approximate inference…

The device-edge co-inference paradigm effectively bridges the gap between the high resource demands of Graph Neural Networks (GNNs) and limited device resources, making it a promising solution for advancing edge GNN applications. Existing…

DNN inference can be accelerated by distributing the workload among a cluster of collaborative edge nodes. Heterogeneity among edge devices and accuracy-performance trade-offs of DNN models present a complex exploration space while catering…

To achieve high accuracy, convolutional neural networks (CNNs) are increasingly growing in complexity and diversity in layer types and topologies. This makes it very challenging to efficiently deploy such networks on custom processor…

There is a growing demand to deploy computation-intensive deep learning (DL) models on resource-constrained mobile devices for real-time intelligent applications. Equipped with a variety of processing units such as CPUs, GPUs, and NPUs, the…

The ever-increasing demand from mobile Machine Learning (ML) applications calls for evermore powerful on-chip computing resources. Mobile devices are empowered with heterogeneous multi-processor Systems-on-Chips (SoCs) to process ML…

This paper presents PreVIous, a methodology to predict the performance of convolutional neural networks (CNNs) in terms of throughput and energy consumption on vision-enabled devices for the Internet of Things. CNNs typically constitute a…

Graph processing requires irregular, fine-grained random access patterns incompatible with contemporary off-chip memory architecture, leading to inefficient data access. This inefficiency makes graph processing an extremely memory-bound…

Distributed inference serves as a promising approach to enabling the inference of large language models (LLMs) at the network edge. It distributes the inference process to multiple devices to ensure that the LLMs can fit into the device…

Machine intelligence, especially using convolutional neural networks (CNNs), has become a large area of research over the past years. Increasingly sophisticated hardware accelerators are proposed that exploit e.g. the sparsity in…

Convolutional Neural Networks (CNN) have been widely deployed in diverse application domains. There has been significant progress in accelerating both their training and inference using high-performance GPUs, FPGAs, and custom ASICs for…

Deploying deep neural networks (DNNs) on resource-constrained mobile devices presents significant challenges, particularly in achieving real-time performance while simultaneously coping with limited computational resources and battery life.…

Accurate multiple-input multiple-output (MIMO) channel estimation is critical for next-generation wireless systems, enabling enhanced communication and sensing performance. Traditional model-based channel estimation methods suffer, however,…

A new, radical CNN design approach is presented in this paper, considering the reduction of the total computational load during inference. This is achieved by a new holistic intervention on both the CNN architecture and the training…