Related papers: CoSS: Co-optimizing Sensor and Sampling Rate for D…

Data sampling is an effective method to improve the training speed of neural networks, with recent results demonstrating that it can even break the neural scaling laws. These results critically rely on high-quality scores to estimate the…

The success of convolutional neural networks (CNNs) in computer vision applications has been accompanied by a significant increase of computation and memory costs, which prohibits its usage on resource-limited environments such as mobile or…

Meta-learning algorithms for active learning are emerging as a promising paradigm for learning the ``best'' active learning strategy. However, current learning-based active learning approaches still require sufficient training data so as to…

The existing action recognition methods are mainly based on clip-level classifiers such as two-stream CNNs or 3D CNNs, which are trained from the randomly selected clips and applied to densely sampled clips during testing. However, this…

Human evaluation is viewed as a reliable evaluation method for NLG which is expensive and time-consuming. To save labor and costs, researchers usually perform human evaluation on a small subset of data sampled from the whole dataset in…

Semantic segmentation of Very High Resolution (VHR) remote sensing images is a fundamental task for many applications. However, large variations in the scales of objects in those VHR images pose a challenge for performing accurate semantic…

Human activity recognition serves an important part in building continuous behavioral monitoring systems, which are deployable for visual surveillance, patient rehabilitation, gaming, and even personally inclined smart homes. This paper…

Training advanced machine learning models demands massive datasets, resulting in prohibitive computational costs. To address this challenge, data pruning techniques identify and remove redundant training samples while preserving model…

Enabling low power wireless devices to adopt Nyquist sampling at high carriers is prohibitive. In spectrum sensing, this limit calls for an analog front-end that can sweep different bands quickly, in order to use the available spectrum…

Sensor selection is an important design problem in large-scale sensor networks. Sensor selection can be interpreted as the problem of selecting the best subset of sensors that guarantees a certain estimation performance. We focus on…

Neural architecture search has attracted wide attentions in both academia and industry. To accelerate it, researchers proposed weight-sharing methods which first train a super-network to reuse computation among different operators, from…

Autonomous driving vehicles aim to free the hands of vehicle operators, helping them to drive easier and faster, meanwhile, improving the safety of driving on the highway or in complex scenarios. Automated driving systems (ADS) are…

Negative sampling has been heavily used to train recommender models on large-scale data, wherein sampling hard examples usually not only accelerates the convergence but also improves the model accuracy. Nevertheless, the reasons for the…

Wireless control systems (WCSs) often have to operate in dynamic environments where the network traffic load may vary unpredictably over time. The sampling in sensors is conventionally time triggered with fixed periods. In this context,…

Decision-makers often encounter uncertainty, and the distribution of uncertain parameters plays a crucial role in making reliable decisions. However, complete information is rarely available. The sample average approximation (SAA) approach…

Recently, Convolutional Neural Networks (CNNs) have shown unprecedented success in the field of computer vision, especially on challenging image classification tasks by relying on a universal approach, i.e., training a deep model on a…

With computers getting more and more powerful and integrated in our daily lives, the focus is increasingly shifting towards more human-friendly interfaces, making Automatic Speech Recognition (ASR) a central player as the ideal means of…

Statistical models are widely used to estimate the performance of commercial off-the-shelf (COTS) AI hardware accelerators. However, training of statistical performance models often requires vast amounts of data, leading to a significant…

Real-time video segmentation is a promising opportunity for AI-assisted surgery, offering intraoperative guidance by identifying tools and anatomical structures. Despite growing interest in surgical video segmentation, annotation protocols…

Human Activity Recognition from body-worn sensor data poses an inherent challenge in capturing spatial and temporal dependencies of time-series signals. In this regard, the existing recurrent or convolutional or their hybrid models for…