Related papers: S2DNAS:Transforming Static CNN Model for Dynamic I…
Multiplication-less neural networks significantly reduce the time and energy cost on the hardware platform, as the compute-intensive multiplications are replaced with lightweight bit-shift operations. However, existing bit-shift networks…
Convolutional neural network (CNN) architectures have traditionally been explored by human experts in a manual search process that is time-consuming and ineffectively explores the massive space of potential solutions. Neural architecture…
Architecture search optimizes the structure of a neural network for some task instead of relying on manual authoring. However, it is slow, as each potential architecture is typically trained from scratch. In this paper we present an…
Practical use of neural networks often involves requirements on latency, energy and memory among others. A popular approach to find networks under such requirements is through constrained Neural Architecture Search (NAS). However, previous…
Dynamic convolution achieves better performance for efficient CNNs at the cost of negligible FLOPs increase. However, the performance increase can not match the significantly expanded number of parameters, which is the main bottleneck in…
Prostate cancer is one of the most common causes of cancer deaths in men. There is a growing demand for noninvasively and accurately diagnostic methods that facilitate the current standard prostate cancer risk assessment in clinical…
In this paper, we propose BNAS-v2 to further improve the efficiency of NAS, embodying both superiorities of BCNN simultaneously. To mitigate the unfair training issue of BNAS, we employ continuous relaxation strategy to make each edge of…
While Convolutional Neural Networks (CNNs) excel at learning complex latent-space representations, their over-parameterization can lead to overfitting and reduced performance, particularly with limited data. This, alongside their high…
Single Image Super-Resolution (SISR) tasks have achieved significant performance with deep neural networks. However, the large number of parameters in CNN-based met-hods for SISR tasks require heavy computations. Although several efficient…
Latent factor models are the driving forces of the state-of-the-art recommender systems, with an important insight of vectorizing raw input features into dense embeddings. The dimensions of different feature embeddings are often set to a…
In this paper we propose a novel network adaption method called Differentiable Network Adaption (DNA), which can adapt an existing network to a specific computation budget by adjusting the width and depth in a differentiable manner. The…
Diffusion models have recently shown remarkable generation ability, achieving state-of-the-art performance in many tasks. However, the high computational cost is still a troubling problem for diffusion models. To tackle this problem, we…
We propose three novel pruning techniques to improve the cost and results of inference-aware Differentiable Neural Architecture Search (DNAS). First, we introduce Prunode, a stochastic bi-path building block for DNAS, which can search over…
Standard Convolutional Neural Network (CNN) designs rarely focus on the importance of explicitly capturing diverse features to enhance the network's performance. Instead, most existing methods follow an indirect approach of increasing or…
With the increasing popularity of deep learning, Convolutional Neural Networks (CNNs) have been widely applied in various domains, such as image classification and object detection, and achieve stunning success in terms of their high…
Neural architecture search (NAS) proves to be among the effective approaches for many tasks by generating an application-adaptive neural architecture, which is still challenged by high computational cost and memory consumption. At the same…
Modern convolutional neural networks (CNNs) are workhorses for video and image processing, but fail to adapt to the computational complexity of input samples in a dynamic manner to minimize energy consumption. In this research, we propose…
Convolutional neural networks (CNNs) are deep learning frameworks which are well-known for their notable performance in classification tasks. Hence, many skeleton-based action recognition and segmentation (SBARS) algorithms benefit from…
Recent works show that convolutional neural network (CNN) architectures have a spectral bias towards lower frequencies, which has been leveraged for various image restoration tasks in the Deep Image Prior (DIP) framework. The benefit of the…
Deep Convolutional Neural Networks (CNN) provides an "end-to-end" solution for image pattern recognition with impressive performance in many areas of application including medical imaging. Most CNN models of high performance use…