Related papers: BDC-Occ: Binarized Deep Convolution Unit For Binar…
Convolutional neural networks have recently achieved significant breakthroughs in various image classification tasks. However, they are computationally expensive,which can make their feasible mplementation on embedded and low-power devices…
Different from other deep scalable architecture-based NAS approaches, Broad Neural Architecture Search (BNAS) proposes a broad scalable architecture which consists of convolution and enhancement blocks, dubbed Broad Convolutional Neural…
Based on the assumption that there exists a neural network that efficiently represents a set of Boolean functions between all binary inputs and outputs, we propose a process for developing and deploying neural networks whose weight…
Joint clustering and feature learning methods have shown remarkable performance in unsupervised representation learning. However, the training schedule alternating between feature clustering and network parameters update leads to unstable…
Recent trends show recognition accuracy increasing even more profoundly. Inference process of Deep Convolutional Neural Networks (DCNN) has a large number of parameters, requires a large amount of computation, and can be very slow. The…
Binary neural networks have attracted tremendous attention due to the efficiency for deploying them on mobile devices. Since the weak expression ability of binary weights and features, their accuracy is usually much lower than that of…
The advent of deep learning has considerably accelerated machine learning development. The deployment of deep neural networks at the edge is however limited by their high memory and energy consumption requirements. With new memory…
Due to the advent of modern embedded systems and mobile devices with constrained resources, there is a great demand for incredibly efficient deep neural networks for machine learning purposes. There is also a growing concern of privacy and…
Convolutional neural networks (CNNs) and transformers, which are composed of multiple processing layers and blocks to learn the representations of data with multiple abstract levels, are the most successful machine learning models in recent…
Binary Neural Networks (BNNs), neural networks with weights and activations constrained to -1(0) and +1, are an alternative to deep neural networks which offer faster training, lower memory consumption and lightweight models, ideal for use…
Human driver can easily describe the complex traffic scene by visual system. Such an ability of precise perception is essential for driver's planning. To achieve this, a geometry-aware representation that quantizes the physical 3D scene…
This paper proposes ReBNet, an end-to-end framework for training reconfigurable binary neural networks on software and developing efficient accelerators for execution on FPGA. Binary neural networks offer an intriguing opportunity for…
Convolutional neural networks (CNNs) have revolutionized the world of computer vision over the last few years, pushing image classification beyond human accuracy. The computational effort of today's CNNs requires power-hungry parallel…
Unmanned Aerial Vehicles (UAVs) have attracted great interest in the last few years owing to their ability to cover large areas and access difficult and hazardous target zones, which is not the case of traditional systems relying on direct…
For binary neural networks (BNNs) to become the mainstream on-device computer vision algorithm, they must achieve a superior speed-vs-accuracy tradeoff than 8-bit quantization and establish a similar degree of general applicability in…
Self-supervised 3D occupancy prediction offers a promising solution for understanding complex driving scenes without requiring costly 3D annotations. However, training dense occupancy decoders to capture fine-grained geometry and semantics…
Verifying and explaining the behavior of neural networks is becoming increasingly important, especially when they are deployed in safety-critical applications. In this paper, we study verification problems for Binarized Neural Networks…
With the increasing popularity and the increasing size of vision transformers (ViTs), there has been an increasing interest in making them more efficient and less computationally costly for deployment on edge devices with limited computing…
We introduce Larq Compute Engine, the world's fastest Binarized Neural Network (BNN) inference engine, and use this framework to investigate several important questions about the efficiency of BNNs and to design a new state-of-the-art BNN…
Convolutional Neural Networks with 3D kernels (3D-CNNs) currently achieve state-of-the-art results in video recognition tasks due to their supremacy in extracting spatiotemporal features within video frames. There have been many successful…