相关论文: $\gamma$-Quant: Towards Learnable Quantization for…

Post-training quantization (PTQ) reduces a model's memory footprint by mapping full precision weights into low bit weights without costly retraining, but can degrade its downstream performance especially in low 2- to 3-bit settings. We…

Few-Shot Learning is the challenge of training a model with only a small amount of data. Many solutions to this problem use meta-learning algorithms, i.e. algorithms that learn to learn. By sampling few-shot tasks from a larger dataset, we…

Computational meta-imagers synergize metamaterial hardware with advanced signal processing approaches such as compressed sensing. Recent advances in artificial intelligence (AI) are gradually reshaping the landscape of meta-imaging. Most…

We propose a sparse-coding framework for activity recognition in ubiquitous and mobile computing that alleviates two fundamental problems of current supervised learning approaches. (i) It automatically derives a compact, sparse and…

This paper explores a novel paradigm in low-bit (i.e. 4-bits or lower) quantization, differing from existing state-of-the-art methods, by framing optimal quantization as an architecture search problem within convolutional neural networks…

Human activity recognition (HAR) research has increased in recent years due to its applications in mobile health monitoring, activity recognition, and patient rehabilitation. The typical approach is training a HAR classifier offline with…

Artificial neural networks bridge input data into output results by approximately encoding the function that relates them. This is achieved after training the network with a collection of known inputs and results leading to an adjustment of…

Quantization using a small number of bits shows promise for reducing latency and memory usage in deep neural networks. However, most quantization methods cannot readily handle complicated functions such as exponential and square root, and…

Quantized low-precision neural networks are very popular because they require less computational resources for inference and can provide high performance, which is vital for real-time and embedded recognition systems. However, their…

What spatial frequency information do humans and neural networks use to recognize objects? In neuroscience, critical band masking is an established tool that can reveal the frequency-selective filters used for object recognition. Critical…

In this paper, we report a hierarchical deep learning model for classification of complex human activities using motion sensors. In contrast to traditional Human Activity Recognition (HAR) models used for event-based activity recognition,…

Neural networks with sub-microsecond inference latency are required by many critical applications. Targeting such applications deployed on FPGAs, we present High Granularity Quantization (HGQ), a quantization-aware training framework that…

Human Activity Recognition (HAR) from wearable sensor data identifies movements or activities in unconstrained environments. HAR is a challenging problem as it presents great variability across subjects. Obtaining large amounts of labelled…

Bandwidth constraints during signal acquisition frequently impede real-time detection applications. Hyperspectral data is a notable example, whose vast volume compromises real-time hyperspectral detection. To tackle this hurdle, we…

Radio-Frequency (RF) based device-free Human Activity Recognition (HAR) rises as a promising solution for many applications. However, device-free (or contactless) sensing is often more sensitive to environment changes than device-based (or…

Quantum hypothesis testing is one of the most fundamental problems in quantum information theory, with crucial implications in areas like quantum sensing, where it has been used to prove quantum advantage in a series of binary photonic…

Human activity recognition (HAR) from on-body sensors is a core functionality in many AI applications: from personal health, through sports and wellness to Industry 4.0. A key problem holding up progress in wearable sensor-based HAR,…

With the AI of Things (AIoT) development, a huge amount of visual data, e.g., images and videos, are produced in our daily work and life. These visual data are not only used for human viewing or understanding but also for machine analysis…

Quantization-aware training (QAT) is a common paradigm for network quantization, in which the training phase incorporates the simulation of the low-precision computation to optimize the quantization parameters in alignment with the task…

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…