Related papers: Window-Based Early-Exit Cascades for Uncertainty E…
We study the tradeoff between computational effort and classification accuracy in a cascade of deep neural networks. During inference, the user sets the acceptable accuracy degradation which then automatically determines confidence…
Traditional machine learning approaches may fail to perform satisfactorily when dealing with complex data. In this context, the importance of data mining evolves w.r.t. building an efficient knowledge discovery and mining framework.…
Ensembles of independently trained deep neural networks yield uncertainty estimates that rival Bayesian networks in performance. They also offer sizable improvements in terms of predictive performance over single models. However, deep…
The deployment of inference services at the network edge, called edge inference, offloads computation-intensive inference tasks from mobile devices to edge servers, thereby enhancing the former's capabilities and battery lives. In a…
Despite deep neural network (DNN)'s impressive prediction performance in various domains, it is well known now that a set of DNN models trained with the same model specification and the same data can produce very different prediction…
Deep neural networks excel in perception tasks such as semantic segmentation and monocular depth estimation, making them indispensable in safety-critical applications like autonomous driving and industrial inspection. However, they often…
Deep neural network ensembles are powerful tools for uncertainty quantification, which have recently been re-interpreted from a Bayesian perspective. However, current methods inadequately leverage second-order information of the loss…
Ensemble methods are arguably the most trustworthy techniques for boosting the performance of machine learning models. Popular independent ensembles (IE) relying on naive averaging/voting scheme have been of typical choice for most…
Recommending items to users has long been a fundamental task, and studies have tried to improve it ever since. Most well-known models commonly employ representation learning to map users and items into a unified embedding space for matching…
Deep neural networks provide state-of-the-art accuracy for vision tasks but they require significant resources for training. Thus, they are trained on cloud servers far from the edge devices that acquire the data. This issue increases…
This paper presents a novel feature fusion-based deep learning model (called CASU2Net) for fault detection in offshore wind turbines. The proposed CASU2Net model benefits of a two-step early fusion to enrich features in the final stage.…
Deep-learning-based data-driven forecasting methods have produced impressive results for traffic forecasting. A major limitation of these methods, however, is that they provide forecasts without estimates of uncertainty, which are critical…
Deep Learning methods are known to suffer from calibration issues: they typically produce over-confident estimates. These problems are exacerbated in the low data regime. Although the calibration of probabilistic models is well studied,…
Ensemble methods, traditionally built with independently trained de-correlated models, have proven to be efficient methods for reducing the remaining residual generalization error, which results in robust and accurate methods for real-world…
Deepfake detection has become increasingly important due to the rise of synthetic media, which poses significant risks to digital identity and cyber presence for security and trust. While multiple approaches have improved detection…
Deep neural networks have been remarkable successful in various AI tasks but often cast high computation and energy cost for energy-constrained applications such as mobile sensing. We address this problem by proposing a novel framework that…
Motion forecasting has become an increasingly critical component of autonomous robotic systems. Onboard compute budgets typically limit the accuracy of real-time systems. In this work we propose methods of improving motion forecasting…
Several real-world classification problems are example-dependent cost-sensitive in nature, where the costs due to misclassification vary between examples and not only within classes. However, standard classification methods do not take…
One of the generally accepted views of modern deep learning is that increasing the number of parameters usually leads to better quality. The two easiest ways to increase the number of parameters is to increase the size of the network, e.g.…
Uncertainty estimation and ensembling methods go hand-in-hand. Uncertainty estimation is one of the main benchmarks for assessment of ensembling performance. At the same time, deep learning ensembles have provided state-of-the-art results…