Related papers: Feature matching as improved transfer learning tec…
In practical sleep stage classification, a key challenge is the variability of EEG data across different subjects and environments. Differences in physiology, age, health status, and recording conditions can lead to domain shifts between…
With the emergence of large-scale pre-trained neural networks, methods to adapt such "foundation" models to data-limited downstream tasks have become a necessity. Fine-tuning, preference optimization, and transfer learning have all been…
Transfer learning of StyleGAN has recently shown great potential to solve diverse tasks, especially in domain translation. Previous methods utilized a source model by swapping or freezing weights during transfer learning, however, they have…
Deep neural networks have led to a series of breakthroughs in computer vision given sufficient annotated training datasets. For novel tasks with limited labeled data, the prevalent approach is to transfer the knowledge learned in the…
Deep neural networks (DNNs) exhibit vulnerability to adversarial examples that can transfer across different DNN models. A particularly challenging problem is developing transferable targeted attacks that can mislead DNN models into…
Transfer learning has become a central paradigm in modern machine learning, yet it suffers from the long-standing problem of negative transfer, where leveraging source representations can harm rather than help performance on the target…
The ability for robots to transfer their learned knowledge to new tasks -- where data is scarce -- is a fundamental challenge for successful robot learning. While fine-tuning has been well-studied as a simple but effective transfer approach…
Deep learning models for scoring sleep stages based on single-channel EEG have been proposed as a promising method for remote sleep monitoring. However, applying these models to new datasets, particularly from wearable devices, raises two…
Parameter-efficient fine-tuning (PEFT) has emerged as an effective method for adapting pre-trained language models to various tasks efficiently. Recently, there has been a growing interest in transferring knowledge from one or multiple…
Adversarial examples (AEs) have been extensively studied due to their potential for privacy protection and inspiring robust neural networks. Yet, making a targeted AE transferable across unknown models remains challenging. In this paper, to…
Parameter fine tuning is a transfer learning approach whereby learned parameters from pre-trained source network are transferred to the target network followed by fine-tuning. Prior research has shown that this approach is capable of…
Feature-based transfer is one of the most effective methodologies for transfer learning. Existing studies usually assume that the learned new feature representation is \emph{domain-invariant}, and thus train a transfer model $\mathcal{M}$…
Transfer learning, a technique commonly used in generative artificial intelligence, allows neural network models to bring prior knowledge to bear when learning a new task. This study demonstrates that transfer learning significantly…
Transfer learning, which allows a source task to affect the inductive bias of the target task, is widely used in computer vision. The typical way of conducting transfer learning with deep neural networks is to fine-tune a model pre-trained…
We consider Heterogeneous Transfer Learning (HTL) from a source to a new target domain for high-dimensional regression with differing feature sets. Most homogeneous TL methods assume that target and source domains share the same feature…
Fine-tuning of self-supervised models is a powerful transfer learning method in a variety of fields, including speech processing, since it can utilize generic feature representations obtained from large amounts of unlabeled data.…
Many sleep studies suffer from the problem of insufficient data to fully utilize deep neural networks as different labs use different recordings set ups, leading to the need of training automated algorithms on rather small databases,…
The focus in machine learning has branched beyond training classifiers on a single task to investigating how previously acquired knowledge in a source domain can be leveraged to facilitate learning in a related target domain, known as…
Cross-entropy (CE) training provides dense and scalable supervision for language models, but it optimizes next-token prediction under teacher forcing rather than sequence-level behavior under model rollouts. We introduce a feature-matching…
The recent popularity of foundation models and the pre-train-and-adapt paradigm, where a large-scale model is transferred to downstream tasks, is gaining attention for volumetric medical image segmentation. However, current transfer…