Related papers: Enhancing Small-Scale Dataset Expansion with Tripl…

Modern deep neural networks rely heavily on massive model weights and training samples, incurring substantial computational costs. Weight pruning and coreset selection are two emerging paradigms proposed to improve computational efficiency.…

Training vision-language models (VLMs) for medical report generation is often hindered by the scarcity of high-quality annotated data. This work evaluates the use of a weighted loss function to improve data efficiency. Compared to standard…

Recent advances in a generative neural network model extend the development of data augmentation methods. However, the augmentation methods based on the modern generative models fail to achieve notable performance for class imbalance data…

Data augmentation plays a crucial role in deep learning, enhancing the generalization and robustness of learning-based models. Standard approaches involve simple transformations like rotations and flips for generating extra data. However,…

Novel architectures have recently improved generative image synthesis leading to excellent visual quality in various tasks. Much of this success is due to the scalability of these architectures and hence caused by a dramatic increase in…

Generative diffusion models offer a natural choice for data augmentation when training complex vision models. However, ensuring reliability of their generative content as augmentation samples remains an open challenge. Despite a number of…

How far are we really from automatically generating neural networks? While neural network weight generation shows promise, current approaches struggle with generalization to unseen tasks and practical application exploration. To address…

Supervised term weighting could improve the performance of text categorization. A way proven to be effective is to give more weight to terms with more imbalanced distributions across categories. This paper shows that supervised term…

Weight averaging is a widely used technique for accelerating training and improving the generalization of deep neural networks (DNNs). While existing approaches like stochastic weight averaging (SWA) rely on pre-set weighting schemes, they…

Most deep neural networks are trained under fixed network architectures and require retraining when the architecture changes. If expanding the network's size is needed, it is necessary to retrain from scratch, which is expensive. To avoid…

Small datasets are common in health research. However, the generalization performance of machine learning models is suboptimal when the training datasets are small. To address this, data augmentation is one solution. Augmentation increases…

Biomedical imaging datasets are often small and biased, meaning that real-world performance of predictive models can be substantially lower than expected from internal testing. This work proposes using generative image editing to simulate…

This paper proposes a novel, efficient transfer learning method, called Scalable Weight Reparametrization (SWR) that is efficient and effective for multiple downstream tasks. Efficient transfer learning involves utilizing a pre-trained…

Data-free compression raises a new challenge because the original training dataset for a pre-trained model to be compressed is not available due to privacy or transmission issues. Thus, a common approach is to compute a reconstructed…

End-to-end generative methods are considered a more promising solution for image restoration in physics-based vision compared with the traditional deconstructive methods based on handcrafted composition models. However, existing generative…

Data augmentation is widely used to enhance generalization in visual classification tasks. However, traditional methods struggle when source and target domains differ, as in domain adaptation, due to their inability to address domain gaps.…

Supervised training of an automated medical image analysis system often requires a large amount of expert annotations that are hard to collect. Moreover, the proportions of data available across different classes may be highly imbalanced…

Neural networks are widespread due to their powerful performance. Yet, they degrade in the presence of noisy labels at training time. Inspired by the setting of learning with expert advice, where multiplicative weights (MW) updates were…

Accurate and robust medical image classification is a challenging task, especially in application domains where available annotated datasets are small and present high imbalance between target classes. Considering that data acquisition is…

Recent studies showcase the competitive accuracy of Vision Transformers (ViTs) in relation to Convolutional Neural Networks (CNNs), along with their remarkable robustness. However, ViTs demand a large amount of data to achieve adequate…