Related papers: A Three-Stage Bayesian Transfer Learning Framework…

Transfer learning enhances model performance in a target population with limited samples by leveraging knowledge from related studies. While many works focus on improving predictive performance, challenges of statistical inference persist.…

Deep learning-based methods deliver state-of-the-art performance for solving inverse problems that arise in computational imaging. These methods can be broadly divided into two groups: (1) learn a network to map measurements to the signal…

Accurate surface roughness prediction is critical for ensuring high product quality, especially in areas like manufacturing and aerospace, where the smallest imperfections can compromise performance or safety. However, this is challenging…

Large-scale labeled training datasets have enabled deep neural networks to excel on a wide range of benchmark vision tasks. However, in many applications it is prohibitively expensive or time-consuming to obtain large quantities of labeled…

Learning predictive models in new domains with scarce training data is a growing challenge in modern supervised learning scenarios. This incentivizes developing domain adaptation methods that leverage the knowledge in known domains (source)…

We propose a cross-domain latent modulation mechanism within a variational autoencoders (VAE) framework to enable improved transfer learning. Our key idea is to procure deep representations from one data domain and use it as perturbation to…

Domain adaptation (DA) aims to transfer discriminative features learned from source domain to target domain. Most of DA methods focus on enhancing feature transferability through domain-invariance learning. However, source-learned…

In recent years, machine learning has achieved impressive results across different application areas. However, machine learning algorithms do not necessarily perform well on a new domain with a different distribution than its training set.…

We develop a novel transfer learning framework to tackle the challenge of limited training data in image reconstruction problems. The proposed framework consists of two training steps, both of which are formed as bi-level optimizations. In…

Neural Architecture Search (NAS) methods have been shown to outperform hand-designed models and help to democratize AI. However, NAS methods often start from scratch with each new task, making them computationally expensive and limiting…

Adversarial learning methods are a promising approach to training robust deep networks, and can generate complex samples across diverse domains. They also can improve recognition despite the presence of domain shift or dataset bias: several…

Standard deep neural networks (DNNs) are commonly trained in an end-to-end fashion for specific tasks such as object recognition, face identification, or character recognition, among many examples. This specificity often leads to…

Unsupervised domain adaption aims to learn a powerful classifier for the target domain given a labeled source data set and an unlabeled target data set. To alleviate the effect of `domain shift', the major challenge in domain adaptation,…

With the rapid development of Deep Learning, more and more applications on the cloud and edge tend to utilize large DNN (Deep Neural Network) models for improved task execution efficiency as well as decision-making quality. Due to memory…

Multi-fidelity machine learning methods address the accuracy-efficiency trade-off by integrating scarce, resource-intensive high-fidelity data with abundant but less accurate low-fidelity data. We propose a practical multi-fidelity strategy…

Deep learning takes advantage of large datasets and computationally efficient training algorithms to outperform other approaches at various machine learning tasks. However, imperfections in the training phase of deep neural networks make…

Existing transfer learning-based beam prediction approaches primarily rely on simple fine-tuning. When there is a significant difference in data distribution between the target domain and the source domain, simple fine-tuning limits the…

Domain Adaptation (DA) enables transferring a learning machine from a labeled source domain to an unlabeled target one. While remarkable advances have been made, most of the existing DA methods focus on improving the target accuracy at…

Deep learning has been applied to achieve significant progress in emotion recognition. Despite such substantial progress, existing approaches are still hindered by insufficient training data, and the resulting models do not generalize well…

Generalized Category Discovery is a crucial real-world task. Despite the improved performance on known categories, current methods perform poorly on novel categories. We attribute the poor performance to two reasons: biased knowledge…