Related papers: Dynamic Restrained Uncertainty Weighting Loss for …

End-to-end visuomotor control is emerging as a compelling solution for robot manipulation tasks. However, imitation learning-based visuomotor control approaches tend to suffer from a common limitation, lacking the ability to recover from an…

Continuous dimensional emotion prediction is a challenging task where the fusion of various modalities usually achieves state-of-the-art performance such as early fusion or late fusion. In this paper, we propose a novel multi-modal fusion…

Binary neural networks (BNNs) constrain weights and activations to +1 or -1 with limited storage and computational cost, which is hardware-friendly for portable devices. Recently, BNNs have achieved remarkable progress and been adopted into…

This paper introduces two learning schemes for distributed agents in Reinforcement Learning (RL) environments, namely Reward-Weighted (R-Weighted) and Loss-Weighted (L-Weighted) gradient merger. The R/L weighted methods replace standard…

In our paper, we focus on robust variable selection for missing data and measurement error. Missing data and measurement errors can lead to confusing data distribution. We propose an exponential loss function with a tuning parameter to…

Training of deep neural networks heavily depends on the data distribution. In particular, the networks easily suffer from class imbalance. The trained networks would recognize the frequent classes better than the infrequent classes. To…

Understanding uncertainty plays a critical role in achieving common ground (Clark et al.,1983). This is especially important for multimodal AI systems that collaborate with users to solve a problem or guide the user through a challenging…

Multi-Agent Reinforcement Learning (MARL) has gained significant traction for solving complex real-world tasks, but the inherent stochasticity and uncertainty in these environments pose substantial challenges to efficient and robust policy…

Deep Learning (DL) has made remarkable achievements in computer vision and adopted in safety critical domains such as medical imaging or autonomous drive. Thus, it is necessary to understand the uncertainty of the model to effectively…

Traditional models for question answering optimize using cross entropy loss, which encourages exact answers at the cost of penalizing nearby or overlapping answers that are sometimes equally accurate. We propose a mixed objective that…

Target imbalance affects the performance of recent deep learning methods in many medical image segmentation tasks. It is a twofold problem: class imbalance - positive class (lesion) size compared to negative class (non-lesion) size; lesion…

In this study, we focus on continuous emotion recognition using body motion and speech signals to estimate Activation, Valence, and Dominance (AVD) attributes. Semi-End-To-End network architecture is proposed where both extracted features…

Multimodal learning systems often face substantial uncertainty due to noisy data, low-quality labels, and heterogeneous modality characteristics. These issues become especially critical in human-computer interaction settings, where data…

Most deep learning-based models for speech enhancement have mainly focused on estimating the magnitude of spectrogram while reusing the phase from noisy speech for reconstruction. This is due to the difficulty of estimating the phase of…

Supervised masking approaches in the time-frequency domain aim to employ deep neural networks to estimate a multiplicative mask to extract clean speech. This leads to a single estimate for each input without any guarantees or measures of…

With increasing complexity of modern communication systems, machine learning algorithms have become a focal point of research. However, performance demands have tightened in parallel to complexity. For some of the key applications targeted…

In this paper, we present a novel deep multimodal framework to predict human emotions based on sentence-level spoken language. Our architecture has two distinctive characteristics. First, it extracts the high-level features from both text…

This paper introduces Bayesian uncertainty modeling using Stochastic Weight Averaging-Gaussian (SWAG) in Natural Language Understanding (NLU) tasks. We apply the approach to standard tasks in natural language inference (NLI) and demonstrate…

In deep multi-task learning, weights of task-specific networks are shared between tasks to improve performance on each single one. Since the question, which weights to share between layers, is difficult to answer, human-designed…

Reward models (RMs) are essential for aligning large language models (LLM) with human expectations. However, existing RMs struggle to capture the stochastic and uncertain nature of human preferences and fail to assess the reliability of…