Related papers: CompOFA: Compound Once-For-All Networks for Faster…

The increasing demand for on-device training of deep neural networks (DNNs) aims to leverage personal data for high-performance applications while addressing privacy concerns and reducing communication latency. However, resource-constrained…

We introduce a fast Self-adapting Forward-Forward Network (SaFF-Net) for medical imaging analysis, mitigating power consumption and resource limitations, which currently primarily stem from the prevalent reliance on back-propagation for…

Training Convolutional Neural Networks (CNN) is a resource intensive task that requires specialized hardware for efficient computation. One of the most limiting bottleneck of CNN training is the memory cost associated with storing the…

Convolutional Neural Networks (CNNs) have proven to be extremely accurate for image recognition, even outperforming human recognition capability. When deployed on battery-powered mobile devices, efficient computer architectures are required…

Neural architecture search (NAS) has been very successful at outperforming human-designed convolutional neural networks (CNN) in accuracy, and when hardware information is present, latency as well. However, NAS-designed CNNs typically have…

Single computation engines have become a popular design choice for FPGA-based convolutional neural networks (CNNs) enabling the deployment of diverse models without fabric reconfiguration. This flexibility, however, often comes with…

Federated learning (FL) is a promising distributed paradigm, eliminating the need for data sharing but facing challenges from data heterogeneity. Personalized parameter generation through a hypernetwork proves effective, yet existing…

The success of neural networks such as convolutional neural networks (CNNs) has been largely attributed to their effective and widespread deployment on customised computing platforms, including field-programmable gate arrays (FPGAs) and…

Successful training of convolutional neural networks is often associated with sufficiently deep architectures composed of high amounts of features. These networks typically rely on a variety of regularization and pruning techniques to…

Various applications in the field of autonomous driving are based on convolutional neural networks (CNNs), especially for processing camera data. The optimization of such CNNs is a major challenge in continuous development. Newly learned…

Adversarial training has been widely acknowledged as the most effective method to improve the adversarial robustness against adversarial examples for Deep Neural Networks (DNNs). So far, most existing works focus on enhancing the overall…

We propose InCA, a lightweight method for transfer learning that cross-attends to any activation layer of a pre-trained model. During training, InCA uses a single forward pass to extract multiple activations, which are passed to external…

We present a method that achieves state-of-the-art results on challenging (few-shot) layout-to-image generation tasks by accurately modeling textures, structures and relationships contained in a complex scene. After compressing RGB images…

The width of a neural network matters since increasing the width will necessarily increase the model capacity. However, the performance of a network does not improve linearly with the width and soon gets saturated. In this case, we argue…

Graph Neural Networks (GNNs) have shown promising performance, but at the cost of resource-intensive operations on graph-scale matrices. To reduce computational overhead, previous studies attempt to sparsify the graph or network parameters,…

Deep Learning has revolutionized the fields of computer vision, natural language understanding, speech recognition, information retrieval and more. Many techniques have evolved over the past decade that made models lighter, faster, and…

Training convolutional neural networks (CNNs) requires intense compute throughput and high memory bandwidth. Especially, convolution layers account for the majority of the execution time of CNN training, and GPUs are commonly used to…

In this work, we pursue a unified paradigm for multimodal pretraining to break the scaffolds of complex task/modality-specific customization. We propose OFA, a Task-Agnostic and Modality-Agnostic framework that supports Task…

This paper introduces a novel federated learning framework termed LoRa-FL designed for training low-rank one-shot image detection models deployed on edge devices. By incorporating low-rank adaptation techniques into one-shot detection…

Neural networks are rapidly gaining popularity in scientific research, but training the models is often very time-consuming. Particularly when the training data samples are large high-dimensional arrays, efficient training methodologies…