Related papers: BitQ: Tailoring Block Floating Point Precision for…
Model compression via quantization and sparsity enhancement has gained an immense interest to enable the deployment of deep neural networks (DNNs) in resource-constrained edge environments. Although these techniques have shown promising…
In deep neural networks (DNNs), there are a huge number of weights and multiply-and-accumulate (MAC) operations. Accordingly, it is challenging to apply DNNs on resource-constrained platforms, e.g., mobile phones. Quantization is a method…
Quantization for deep neural networks (DNN) have enabled developers to deploy models with less memory and more efficient low-power inference. However, not all DNN designs are friendly to quantization. For example, the popular Mobilenet…
This work targets the commonly used FPGA (field-programmable gate array) devices as the hardware platform for DNN edge computing. We focus on DNN quantization as the main model compression technique. The novelty of this work is: We use a…
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…
Object detection is one of the key tasks in many applications of computer vision. Deep Neural Networks (DNNs) are undoubtedly a well-suited approach for object detection. However, such DNNs need highly adapted hardware together with…
Model quantization reduces the bit-width of weights and activations, improving memory efficiency and inference speed in diffusion models. However, achieving 4-bit quantization remains challenging. Existing methods, primarily based on…
We study the problem of training and certifying adversarially robust quantized neural networks (QNNs). Quantization is a technique for making neural networks more efficient by running them using low-bit integer arithmetic and is therefore…
Binary neural networks (BNNs) have 1-bit weights and activations. Such networks are well suited for FPGAs, as their dominant computations are bitwise arithmetic and the memory requirement is also significantly reduced. However, compared to…
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…
With ever-increasing computational demand for deep learning, it is critical to investigate the implications of the numeric representation and precision of DNN model weights and activations on computational efficiency. In this work, we…
The resource requirements of deep neural networks (DNNs) pose significant challenges to their deployment on edge devices. Common approaches to address this issue are pruning and mixed-precision quantization, which lead to latency and memory…
Quantization is a crucial technique for deploying deep learning models on resource-constrained devices, such as embedded FPGAs. Prior efforts mostly focus on quantizing matrix multiplications, leaving other layers like BatchNorm or…
To alleviate the practical constraints for deploying deep neural networks (DNNs) on edge devices, quantization is widely regarded as one promising technique. It reduces the resource requirements for computational power and storage space by…
Deep neural network (DNN) deployment has been confined to larger hardware devices due to their expensive computational requirements. This challenge has recently reached another scale with the emergence of large language models (LLMs). In…
Extreme edge platforms, such as in-vehicle smart devices, require efficient deployment of quantized deep neural networks (DNNs) to enable intelligent applications with limited amounts of energy, memory, and computing resources. However,…
We present a differentiable joint pruning and quantization (DJPQ) scheme. We frame neural network compression as a joint gradient-based optimization problem, trading off between model pruning and quantization automatically for hardware…
Deep neural networks (DNNs) offer the highest performance in a wide range of applications in computer vision. These results rely on over-parameterized backbones, which are expensive to run. This computational burden can be dramatically…
Low precision data representation is important to reduce storage size and memory access for convolutional neural networks (CNNs). Yet, existing methods have two major limitations: (1) requiring re-training to maintain accuracy for deep…
Model quantization helps to reduce model size and latency of deep neural networks. Mixed precision quantization is favorable with customized hardwares supporting arithmetic operations at multiple bit-widths to achieve maximum efficiency. We…