Related papers: Improving Domain Generalization for Sound Classifi…

Denoising diffusion probabilistic models have been recently proposed to generate high-quality samples by estimating the gradient of the data density. The framework defines the prior noise as a standard Gaussian distribution, whereas the…

Unsupervised domain adaptation (UDA) aims to leverage the knowledge learned from labeled source domains to improve performance on the unlabeled target domains. While Convolutional Neural Networks (CNNs) have been dominant in previous UDA…

Over-parameterized neural network models often lead to significant performance discrepancies between training and test sets, a phenomenon known as overfitting. To address this, researchers have proposed numerous regularization techniques…

The challenge of overfitting, in which the model memorizes the training data and fails to generalize to test data, has become increasingly significant in the training of large neural networks. To tackle this challenge, Sharpness-Aware…

Transformer-based models have been widely adopted for sentiment analysis tasks due to their exceptional ability to capture contextual information. However, these methods often exhibit suboptimal accuracy in certain scenarios. By analyzing…

Attention mechanism is a fundamental component of the transformer model and plays a significant role in its success. However, the theoretical understanding of how attention learns to select tokens is still an emerging area of research. In…

Crowdsourcing provides a practical way to obtain large amounts of labeled data at a low cost. However, the annotation quality of annotators varies considerably, which imposes new challenges in learning a high-quality model from the…

Multi-rater medical image segmentation captures the inherent ambiguity of clinical interpretation, where diagnostic boundaries vary across experts and imaging devices. Existing approaches often reduce this diversity to consensus labels or…

Federated Learning (FL) can be coordinated under the orchestration of a central server to collaboratively build a privacy-preserving model without the need for data exchange. However, participant data heterogeneity leads to local optima…

Domain generalization (DG) has been a hot topic in image recognition, with a goal to train a general model that can perform well on unseen domains. Recently, federated learning (FL), an emerging machine learning paradigm to train a global…

Generalizing to out-of-distribution data while being aware of model fairness is a significant and challenging problem in meta-learning. The goal of this problem is to find a set of fairness-aware invariant parameters of classifier that is…

Sharpness-aware minimization (SAM) reports improving domain generalization by reducing the loss surface curvature in the parameter space. However, generalization during fine-tuning is often more dependent on the transferability of…

State-of-the-art (SOTA) video denoising methods employ multi-frame simultaneous denoising mechanisms, resulting in significant delays (e.g., 16 frames), making them impractical for real-time cameras. To overcome this limitation, we propose…

NLP models excel on tasks with clean inputs, but are less accurate with noisy inputs. In particular, character-level noise such as human-written typos and adversarially-engineered realistic-looking misspellings often appears in text and can…

Foundation models (FMs), that are trained on broad data at scale and are adaptable to a wide range of downstream tasks, have brought large interest in the research community. Benefiting from the diverse data sources such as different…

End-to-end speaker diarization approaches have shown exceptional performance over the traditional modular approaches. To further improve the performance of the end-to-end speaker diarization for real speech recordings, recently works have…

Operator learning is a data-driven approximation of mappings between infinite-dimensional function spaces, such as the solution operators of partial differential equations. Kernel-based operator learning can offer accurate, theoretically…

Diffusion models achieve superior generation quality but suffer from slow generation speed due to the iterative nature of denoising. In contrast, consistency models, a new generative family, achieve competitive performance with…

Training deep neural networks with spatio-temporal (i.e., 3D) or multidimensional convolutions of higher-order is computationally challenging due to millions of unknown parameters across dozens of layers. To alleviate this, one approach is…

Diffusion models achieve state-of-the-art image quality. However, sampling is costly at inference time because it requires a large number of function evaluations (NFEs). To reduce NFEs, classical ODE numerical methods have been adopted.…