Related papers: VALERIAN: Invariant Feature Learning for IMU Senso…
Despite the vast literature on Human Activity Recognition (HAR) with wearable inertial sensor data, it is perhaps surprising that there are few studies investigating semisupervised learning for HAR, particularly in a challenging scenario…
Recent advances in deep learning have relied on large, labelled datasets to train high-capacity models. However, collecting large datasets in a time- and cost-efficient manner often results in label noise. We present a method for learning…
The performance of deep neural networks scales with dataset size and label quality, rendering the efficient mitigation of low-quality data annotations crucial for building robust and cost-effective systems. Existing strategies to address…
The ability of learning from noisy labels is very useful in many visual recognition tasks, as a vast amount of data with noisy labels are relatively easy to obtain. Traditionally, the label noises have been treated as statistical outliers,…
Active learning aims to train a classifier as fast as possible with as few labels as possible. The core element in virtually any active learning strategy is the criterion that measures the usefulness of the unlabeled data based on which new…
Lameness and gait irregularities are significant concerns in equine health management, affecting performance, welfare, and economic value. Traditional observational methods rely on subjective expert assessments, which can lead to…
Label Distribution Learning (LDL) aims to characterize the polysemy of an instance by building a set of descriptive degrees corresponding to the instance. In recent years, researchers seek to model to obtain an accurate label distribution…
In large-scale supervised learning, penalized logistic regression (PLR) effectively mitigates overfitting through regularization, yet its performance critically depends on robust variable selection. This paper demonstrates that label noise…
Human Activity Recognition (HAR) has recently received remarkable attention in numerous applications such as assisted living and remote monitoring. Existing solutions based on sensors and vision technologies have obtained achievements but…
Large amounts of labeled training data are one of the main contributors to the great success that deep models have achieved in the past. Label acquisition for tasks other than benchmarks can pose a challenge due to requirements of both…
The existence of noisy labels in real-world data negatively impacts the performance of deep learning models. Although much research effort has been devoted to improving robustness to noisy labels in classification tasks, the problem of…
Human activity recognition (HAR) is often limited by the scarcity of labeled datasets due to the high cost and complexity of real-world data collection. To mitigate this, recent work has explored generating virtual inertial measurement unit…
Label noise is one of the key factors that lead to the poor generalization of deep learning models. Existing label-noise learning methods usually assume that the ground-truth classes of the training data are balanced. However, the…
Vision-and-Language Navigation (VLN) is a task where an agent navigates in an embodied indoor environment under human instructions. Previous works ignore the distribution of sample difficulty and we argue that this potentially degrade their…
Human Activity Recognition (HAR) using deep neural network has become a hot topic in human-computer interaction. Machine can effectively identify human naturalistic activities by learning from a large collection of sensor data. Activity…
Despite the large progress in supervised learning with neural networks, there are significant challenges in obtaining high-quality, large-scale and accurately labelled datasets. In such a context, how to learn in the presence of noisy…
Large-scale datasets possessing clean label annotations are crucial for training Convolutional Neural Networks (CNNs). However, labeling large-scale data can be very costly and error-prone, and even high-quality datasets are likely to…
While there has been remarkable progress in the performance of visual recognition algorithms, the state-of-the-art models tend to be exceptionally data-hungry. Large labeled training datasets, expensive and tedious to produce, are required…
We present a novel approach for training deep neural networks in a Bayesian way. Classical, i.e. non-Bayesian, deep learning has two major drawbacks both originating from the fact that network parameters are considered to be deterministic.…
Human activity recognition (HAR) is a time series classification task that focuses on identifying the motion patterns from human sensor readings. Adequate data is essential but a major bottleneck for training a generalizable HAR model,…