Related papers: Data-Free Quantization with Accurate Activation Cl…
Quantization-Aware Training (QAT) has driven much attention to produce efficient neural networks. Current QAT still obtains inferior performances compared with the Full Precision (FP) counterpart. In this work, we argue that quantization…
Zero-shot quantization aims to learn a quantized model from a pre-trained full-precision model with no access to original real training data. The common idea in zero-shot quantization approaches is to generate synthetic data for quantizing…
Generative neural image compression supports data representation at extremely low bitrate, synthesizing details at the client and consistently producing highly realistic images. By leveraging the similarities between quantization error and…
Although convolutional neural networks (CNNs) are now widely used in various computer vision applications, its huge resource demanding on parameter storage and computation makes the deployment on mobile and embedded devices difficult.…
Quantization is a technique for creating efficient Deep Neural Networks (DNNs), which involves performing computations and storing tensors at lower bit-widths than f32 floating point precision. Quantization reduces model size and inference…
In this work we present In-Place Activated Batch Normalization (InPlace-ABN) - a novel approach to drastically reduce the training memory footprint of modern deep neural networks in a computationally efficient way. Our solution substitutes…
Quantization is a widely adopted technique for deep neural networks to reduce the memory and computational resources required. However, when quantized, most models would need a suitable calibration process to keep their performance intact,…
As speech processing systems in mobile and edge devices become more commonplace, the demand for unintrusive speech quality monitoring increases. Deep learning methods provide high-quality estimates of objective and subjective speech quality…
Annotating medical images demands significant time and expertise, often requiring pathologists to invest hundreds of hours in labeling mammary epithelial nuclei datasets. We address this critical challenge by achieving 95.5% Dice score…
We propose a simple data augmentation technique that can be applied to standard model-free reinforcement learning algorithms, enabling robust learning directly from pixels without the need for auxiliary losses or pre-training. The approach…
To improve the execution speed and efficiency of neural networks in embedded systems, it is crucial to decrease the model size and computational complexity. In addition to conventional compression techniques, e.g., weight pruning and…
Weight quantization is one of the most important techniques of Deep Neural Networks (DNNs) model compression method. A recent work using systematic framework of DNN weight quantization with the advanced optimization algorithm ADMM…
Data augmentation is an effective and universal technique for improving generalization performance of deep neural networks. It could enrich diversity of training samples that is essential in medical image segmentation tasks because 1) the…
A recurring problem faced when training neural networks is that there is typically not enough data to maximize the generalization capability of deep neural networks(DNN). There are many techniques to address this, including data…
This paper proposes a training method having multiple cyclic training for achieving enhanced performance in low-bit quantized convolutional neural networks (CNNs). Quantization is a popular method for obtaining lightweight CNNs, where the…
Target classification is a fundamental task in radar systems, and its performance critically depends on the quantization precision of the signal. While high-precision quantization (e.g. 16-bit) is well established, 1-bit quantization offers…
Binarization is an extreme network compression approach that provides large computational speedups along with energy and memory savings, albeit at significant accuracy costs. We investigate the question of where to binarize inputs at…
Tokenization-free hierarchical models are emerging as a promising alternative to traditional Large Language Models (LLMs), addressing inherent preprocessing issues such as vocabulary design complexity, out-of-vocabulary (OOV) errors, and…
Neural networks have shown great performance in cognitive tasks. When deploying network models on mobile devices with limited resources, weight quantization has been widely adopted. Binary quantization obtains the highest compression but…
We present an overview of techniques for quantizing convolutional neural networks for inference with integer weights and activations. Per-channel quantization of weights and per-layer quantization of activations to 8-bits of precision…