Related papers: Zero-shot Quantization: A Comprehensive Survey

Memoryless scalar quantization (MSQ) is a common technique to quantize frame coefficients of signals (which are used as a model for generalized linear samples), making them compatible with our digital technology. The process of quantization…

Quantization is a widely used compression method that effectively reduces redundancies in over-parameterized neural networks. However, existing quantization techniques for deep neural networks often lack a comprehensive error analysis due…

Zero-shot text learning enables text classifiers to handle unseen classes efficiently, alleviating the need for task-specific training data. A simple approach often relies on comparing embeddings of query (text) to those of potential…

Model quantization reduces neural network parameter precision to achieve compression, but often compromises accuracy. Existing post-training quantization (PTQ) methods employ iterative parameter updates to preserve accuracy under high…

Post-training quantization (PTQ) is a neural network compression technique that converts a full-precision model into a quantized model using lower-precision data types. Although it can help reduce the size and computational cost of deep…

Existing neural networks are memory-consuming and computationally intensive, making deploying them challenging in resource-constrained environments. However, there are various methods to improve their efficiency. Two such methods are…

Quantization is an effective technique to reduce memory footprint, inference latency, and power consumption of deep learning models. However, existing quantization methods suffer from accuracy degradation compared to full-precision (FP)…

End-to-end neural network models achieve improved performance on various automatic speech recognition (ASR) tasks. However, these models perform poorly on edge hardware due to large memory and computation requirements. While quantizing…

Zero-Shot Learning (ZSL) presents the challenge of identifying categories not seen during training. This task is crucial in domains where it is costly, prohibited, or simply not feasible to collect training data. ZSL depends on a mapping…

Network quantization is an essential procedure in deep learning for development of efficient fixed-point inference models on mobile or edge platforms. However, as datasets grow larger and privacy regulations become stricter, data sharing…

One of important areas of machine learning research is zero-shot learning. It is applied when properly labeled training data set is not available. A number of zero-shot algorithms have been proposed and experimented with. However, none of…

In Generalized Zero-Shot Learning (GZSL), unseen categories (for which no visual data are available at training time) can be predicted by leveraging their class embeddings (e.g., a list of attributes describing them) together with a…

Neural network quantization aims to accelerate and trim full-precision neural network models by using low bit approximations. Methods adopting the quantization aware training (QAT) paradigm have recently seen a rapid growth, but are often…

Action recognition in surveillance video makes our life safer by detecting the criminal events or predicting violent emergencies. However, efficient action recognition is not free of difficulty. First, there are so many action classes in…

Recently, zero-shot (or training-free) Neural Architecture Search (NAS) approaches have been proposed to liberate NAS from the expensive training process. The key idea behind zero-shot NAS approaches is to design proxies that can predict…

Network quantization, which aims to reduce the bit-lengths of the network weights and activations, has emerged for their deployments to resource-limited devices. Although recent studies have successfully discretized a full-precision…

Zero-shot learning is a learning regime that recognizes unseen classes by generalizing the visual-semantic relationship learned from the seen classes. To obtain an effective ZSL model, one may resort to curating training samples from…

Zero-shot learning (ZSL) which aims to recognize unseen object classes by only training on seen object classes, has increasingly been of great interest in Machine Learning, and has registered with some successes. Most existing ZSL methods…

In this short note, we propose a new method for quantizing the weights of a fully trained neural network. A simple deterministic pre-processing step allows us to quantize network layers via memoryless scalar quantization while preserving…

How to efficiently serve ever-larger trained natural language models in practice has become exceptionally challenging even for powerful cloud servers due to their prohibitive memory/computation requirements. In this work, we present an…