Related papers: FSL-HDnn: A 40 nm Few-shot On-Device Learning Acce…

Recently, lightweight methods for single image super-resolution (SISR) have gained significant popularity and achieved impressive performance due to limited hardware resources. These methods demonstrate that adopting residual feature…

Few-shot learning (FSL) enables object detection models to recognize novel classes given only a few annotated examples, thereby reducing expensive manual data labeling. This survey examines recent FSL advances for video and 3D object…

The computational demands of computer vision tasks based on state-of-the-art Convolutional Neural Network (CNN) image classification far exceed the energy budgets of mobile devices. This paper proposes FixyNN, which consists of a…

Meta-learning offers a promising avenue for few-shot learning (FSL), enabling models to glean a generalizable feature embedding through episodic training on synthetic FSL tasks in a source domain. Yet, in practical scenarios where the…

We present a new efficient OpenCL-based Accelerator for large scale Convolutional Neural Networks called Fast Inference on FPGAs for Convolution Neural Network (FFCNN). FFCNN is based on a deeply pipelined OpenCL kernels architecture. As…

We introduce an automated tool for deploying ultra low-latency, low-power deep neural networks with convolutional layers on FPGAs. By extending the hls4ml library, we demonstrate an inference latency of $5\,\mu$s using convolutional…

With the recently massive development in convolution neural networks, numerous lightweight CNN-based image super-resolution methods have been proposed for practical deployments on edge devices. However, most existing methods focus on one…

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…

In Federated Learning (FL), devices that participate in the training usually have heterogeneous resources, i.e., energy availability. In current deployments of FL, devices that do not fulfill certain hardware requirements are often dropped…

Designing hardware accelerators for deep neural networks (DNNs) has been much desired. Nonetheless, most of these existing accelerators are built for either convolutional neural networks (CNNs) or recurrent neural networks (RNNs). Recently,…

The encoder-decoder framework is state-of-the-art for offline semantic image segmentation. Since the rise in autonomous systems, real-time computation is increasingly desirable. In this paper, we introduce fast segmentation convolutional…

Contemporary Deep Neural Network (DNN) contains millions of synaptic connections with tens to hundreds of layers. The large computation and memory requirements pose a challenge to the hardware design. In this work, we leverage the intrinsic…

The rapid advancements in artificial intelligence (AI), particularly the Large Language Models (LLMs), have profoundly affected our daily work and communication forms. However, it is still a challenge to deploy LLMs on resource-constrained…

Deep learning methods have been successfully applied to hyperspectral image (HSI) classification with remarkable performance. Because of limited labelled HSI data, earlier studies primarily adopted a patch-based classification framework,…

In many real-world problems, collecting a large number of labeled samples is infeasible. Few-shot learning (FSL) is the dominant approach to address this issue, where the objective is to quickly adapt to novel categories in presence of a…

Large models such as Vision Transformers (ViTs) have demonstrated remarkable superiority over smaller architectures like ResNet in few-shot classification, owing to their powerful representational capacity. However, fine-tuning such large…

Large language models (LLMs) have demonstrated exceptional proficiency in understanding and generating human language, but efficient inference on resource-constrained embedded devices remains challenging due to large model sizes and…

Machine learning models differ in terms of accuracy, computational/memory complexity, training time, and adaptability among other characteristics. For example, neural networks (NNs) are well-known for their high accuracy due to the quality…

Federated learning (FL) has emerged as a promising approach to collaboratively train machine learning models across multiple edge devices while preserving privacy. The success of FL hinges on the efficiency of participating models and their…

Anxiety disorders impact millions globally, yet traditional diagnosis relies on clinical interviews, while machine learning models struggle with overfitting due to limited data. Large-scale data collection remains costly and time-consuming,…