相关论文: Resource-efficient domain adaptive pre-training fo…

The accuracy of deep learning (e.g., convolutional neural networks) for an image classification task critically relies on the amount of labeled training data. Aiming to solve an image classification task on a new domain that lacks labeled…

Foundation models (FMs) have shown prominent success in a wide range of tasks. Their applicability to specific domain-task pairings relies on the availability of, both, high-quality data and significant computational resources. These…

Limited labeled data makes it hard to train models from scratch in medical domain, and an important paradigm is pre-training and then fine-tuning. Large pre-trained models contain rich representations, which can be adapted to downstream…

Domain adaptation (DA) is an important technique for modern machine learning-based medical data analysis, which aims at reducing distribution differences between different medical datasets. A proper domain adaptation method can…

Remarkable successes were made in Medical Image Classification (MIC) recently, mainly due to wide applications of convolutional neural networks (CNNs). However, adversarial examples (AEs) exhibited imperceptible similarity with raw data,…

Domain-Adaptive Pre-training (DAP) has recently gained attention for its effectiveness in fine-tuning pre-trained models. Building on this, continual DAP has been explored to develop pre-trained models capable of incrementally incorporating…

Domain adaptation (DA) techniques have the potential in machine learning to alleviate distribution differences between training and test sets by leveraging information from source domains. In image classification, most advances in DA have…

Self-supervised pre-training of deep learning models with contrastive learning is a widely used technique in image analysis. Current findings indicate a strong potential for contrastive pre-training on medical images. However, further…

In medical imaging, the heterogeneity of multi-centre data impedes the applicability of deep learning-based methods and results in significant performance degradation when applying models in an unseen data domain, e.g. a new centreor a new…

Traditional machine learning assumes that training and test sets are derived from the same distribution; however, this assumption does not always hold in practical applications. This distribution disparity can lead to severe performance…

Language models are pre-trained using large corpora of generic data like book corpus, common crawl and Wikipedia, which is essential for the model to understand the linguistic characteristics of the language. New studies suggest using…

In medical image segmentation tasks, the scarcity of labeled training data poses a significant challenge when training deep neural networks. When using U-Net-style architectures, it is common practice to address this problem by pretraining…

This paper presents a detection-aware pre-training (DAP) approach, which leverages only weakly-labeled classification-style datasets (e.g., ImageNet) for pre-training, but is specifically tailored to benefit object detection tasks. In…

LiDAR-based 3D object detectors have been largely utilized in various applications, including autonomous vehicles or mobile robots. However, LiDAR-based detectors often fail to adapt well to target domains with different sensor…

Top-performing deep architectures are trained on massive amounts of labeled data. In the absence of labeled data for a certain task, domain adaptation often provides an attractive option given that labeled data of similar nature but from a…

Applying an object detector, which is neither trained nor fine-tuned on data close to the final application, often leads to a substantial performance drop. In order to overcome this problem, it is necessary to consider a shift between…

In this work, we explore the usage of the Frequency Transformation for reducing the domain shift between the source and target domain (e.g., synthetic image and real image respectively) towards solving the Domain Adaptation task. Most of…

Personalizing diffusion models using limited data presents significant challenges, including overfitting, loss of prior knowledge, and degradation of text alignment. Overfitting leads to shifts in the noise prediction distribution,…

In uses of pre-trained machine learning models, it is a known issue that the target population in which the model is being deployed may not have been reflected in the source population with which the model was trained. This can result in a…

Domain-adaptive continual pretraining (DAPT) is a state-of-the-art technique that further trains a language model (LM) on its pretraining task, e.g., masked language modeling (MLM), when common domain adaptation via LM fine-tuning is not…