Related papers: Neural Architecture Search on Efficient Transforme…

With the flourish of differentiable neural architecture search (NAS), automatically searching latency-constrained architectures gives a new perspective to reduce human labor and expertise. However, the searched architectures are usually…

As the application area of convolutional neural networks (CNN) is growing in embedded devices, it becomes popular to use a hardware CNN accelerator, called neural processing unit (NPU), to achieve higher performance per watt than CPUs or…

Traditional neural architecture search (NAS) has a significant impact in computer vision by automatically designing network architectures for various tasks. In this paper, binarized neural architecture search (BNAS), with a search space of…

Deep learning methods have become very successful at solving many complex tasks such as image classification and segmentation, speech recognition and machine translation. Nevertheless, manually designing a neural network for a specific…

Many studies estimate energy consumption using proxy metrics like memory usage, FLOPs, and inference latency, with the assumption that reducing these metrics will also lower energy consumption in neural networks. This paper, however, takes…

Neural Architecture Search (NAS) has shown great potentials in automatically designing scalable network architectures for dense image predictions. However, existing NAS algorithms usually compromise on restricted search space and search on…

Transformer has shown great successes in natural language processing, computer vision, and audio processing. As one of its core components, the softmax attention helps to capture long-range dependencies yet prohibits its scale-up due to the…

We propose a novel hardware and software co-exploration framework for efficient neural architecture search (NAS). Different from existing hardware-aware NAS which assumes a fixed hardware design and explores the neural architecture search…

Recent works have highlighted the strength of the Transformer architecture on sequence tasks while, at the same time, neural architecture search (NAS) has begun to outperform human-designed models. Our goal is to apply NAS to search for a…

Since its introduction, softmax attention has become the backbone of modern transformer architectures due to its expressiveness and scalability across a wide range of tasks. However, the main drawback of softmax attention is the quadratic…

Differentiable architecture search (DARTS) is successfully applied in many vision tasks. However, directly using DARTS for Transformers is memory-intensive, which renders the search process infeasible. To this end, we propose a multi-split…

Deep learning has become in recent years a cornerstone tool fueling key innovations in the industry, such as autonomous driving. To attain good performances, the neural network architecture used for a given application must be chosen with…

Benefiting from the search efficiency, differentiable neural architecture search (NAS) has evolved as the most dominant alternative to automatically design competitive deep neural networks (DNNs). We note that DNNs must be executed under…

Neural architecture search (NAS) has shown great promise in the field of automated machine learning (AutoML). NAS has outperformed hand-designed networks and made a significant step forward in the field of automating the design of deep…

Most existing neural architecture search (NAS) benchmarks and algorithms prioritize well-studied tasks, e.g. image classification on CIFAR or ImageNet. This makes the performance of NAS approaches in more diverse areas poorly understood. In…

Neural networks (NNs) with intensive multiplications (e.g., convolutions and transformers) are capable yet power hungry, impeding their more extensive deployment into resource-constrained devices. As such, multiplication-free networks,…

Vision Transformer (ViT) demonstrates that Transformer for natural language processing can be applied to computer vision tasks and result in comparable performance to convolutional neural networks (CNN), which have been studied and adopted…

Binary Neural Networks (BNNs) have gained extensive attention for their superior inferencing efficiency and compression ratio compared to traditional full-precision networks. However, due to the unique characteristics of BNNs, designing a…

In neural architecture search, the structure of the neural network to best model a given dataset is determined by an automated search process. Efficient Neural Architecture Search (ENAS), proposed by Pham et al. (2018), has recently…

Transfer learning can boost the performance on the targettask by leveraging the knowledge of the source domain. Recent worksin neural architecture search (NAS), especially one-shot NAS, can aidtransfer learning by establishing sufficient…