Related papers: Transfer or Self-Supervised? Bridging the Performa…
Human adaptability relies crucially on learning and merging knowledge from both supervised and unsupervised tasks: the parents point out few important concepts, but then the children fill in the gaps on their own. This is particularly…
Transfer learning is crucial for medical imaging, yet the selection of source datasets often relies on researchers' intuition rather than systematic principles, which can impact the generalizability of algorithms and, thus, patient…
The advent of federated learning has facilitated large-scale data exchange amongst machine learning models while maintaining privacy. Despite its brief history, federated learning is rapidly evolving to make wider use more practical. One of…
Deep learning methodologies have been employed in several different fields, with an outstanding success in image recognition applications, such as material quality control, medical imaging, autonomous driving, etc. Deep learning models rely…
Semi-supervised learning (SSL) has achieved significant progress in medical image segmentation (SSMIS) through effective utilization of limited labeled data. While current SSL methods for medical images predominantly rely on consistency…
Transfer learning is a valuable tool in deep learning as it allows propagating information from one "source dataset" to another "target dataset", especially in the case of a small number of training examples in the latter. Yet,…
Generalising deep models to new data from new centres (termed here domains) remains a challenge. This is largely attributed to shifts in data statistics (domain shifts) between source and unseen domains. Recently, gradient-based…
Knowledge transfer impacts the performance of deep learning -- the state of the art for image classification tasks, including automated melanoma screening. Deep learning's greed for large amounts of training data poses a challenge for…
If our models are used in new or unexpected cases, do we know if they will make fair predictions? Previously, researchers developed ways to debias a model for a single problem domain. However, this is often not how models are trained and…
Transfer learning aims to transfer knowledge or information from a source domain to a relevant target domain. In this paper, we understand transfer learning from the perspectives of knowledge transferability and trustworthiness. This…
Transfer learning, also referred as knowledge transfer, aims at reusing knowledge from a source dataset to a similar target one. While many empirical studies illustrate the benefits of transfer learning, few theoretical results are…
Transfer learning is aimed to make use of valuable knowledge in a source domain to help model performance in a target domain. It is particularly important to neural networks, which are very likely to be overfitting. In some fields like…
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…
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…
Pre-trained machine learning (ML) models have shown great performance for a wide range of applications, in particular in natural language processing (NLP) and computer vision (CV). Here, we study how pre-training could be used for…
In this work we show that semi-supervised models for vehicle trajectory prediction significantly improve performance over supervised models on state-of-the-art real-world benchmarks. Moving from supervised to semi-supervised models allows…
Self-supervised learning is a powerful paradigm for representation learning on unlabelled images. A wealth of effective new methods based on instance matching rely on data-augmentation to drive learning, and these have reached a rough…
Memory-based self-evolution has emerged as a promising paradigm for coding agents. However, existing approaches typically restrict memory utilization to homogeneous task domains, failing to leverage the shared infrastructural foundations,…
Contrastive visual pretraining based on the instance discrimination pretext task has made significant progress. Notably, recent work on unsupervised pretraining has shown to surpass the supervised counterpart for finetuning downstream…
Transfer learning research attempts to make model induction transferable across different domains. This method assumes that specific information regarding to which domain each instance belongs is known. This paper helps to extend the…