Related papers: Factors of Transferability for a Generic ConvNet R…
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…
We propose a transfer learning method that utilizes data representations in a semiparametric regression model. Our aim is to perform statistical inference on the parameter of primary interest in the target model while accounting for…
Conditional GANs are widely used in translating an image from one category to another. Meaningful conditions to GANs provide greater flexibility and control over the nature of the target domain synthetic data. Existing conditional GANs…
Convolutional neural networks (CNNs) have been recently used for a variety of histology image analysis. However, availability of a large dataset is a major prerequisite for training a CNN which limits its use by the computational pathology…
Visual attributes play an essential role in real applications based on image retrieval. For instance, the extraction of attributes from images allows an eCommerce search engine to produce retrieval results with higher precision. The…
Pre-training a deep neural network on the ImageNet dataset is a common practice for training deep learning models, and generally yields improved performance and faster training times. The technique of pre-training on one task and then…
Deep networks trained on large-scale data can learn transferable features to promote learning multiple tasks. Since deep features eventually transition from general to specific along deep networks, a fundamental problem of multi-task…
Vision transformers (ViTs) have found only limited practical use in processing images, in spite of their state-of-the-art accuracy on certain benchmarks. The reason for their limited use include their need for larger training datasets and…
Deep convolutional neural networks (DCNNs) have attracted much attention in remote sensing recently. Compared with the large-scale annotated dataset in natural images, the lack of labeled data in remote sensing becomes an obstacle to train…
The convolution operation is a central building block of neural network architectures widely used in computer vision. The size of the convolution kernels determines both the expressiveness of convolutional neural networks (CNN), as well as…
Over the past decade, the field of machine learning has experienced remarkable advancements. While image recognition systems have achieved impressive levels of accuracy, they continue to rely on extensive training datasets. Additionally, a…
Modern machine learning models for computer vision exceed humans in accuracy on specific visual recognition tasks, notably on datasets like ImageNet. However, high accuracy can be achieved in many ways. The particular decision function…
In the last decade, convolutional neural networks (ConvNets) have dominated and achieved state-of-the-art performances in a variety of medical imaging applications. However, the performances of ConvNets are still limited by lacking the…
Convolutional neural networks (CNNs) have constantly achieved better performance over years by introducing more complex topology, and enlarging the capacity towards deeper and wider CNNs. This makes the manual design of CNNs extremely…
Transfer learning plays a key role in advancing machine learning models, yet conventional supervised pretraining often undermines feature transferability by prioritizing features that minimize the pretraining loss. In this work, we adapt a…
Transformer, an attention-based encoder-decoder model, has already revolutionized the field of natural language processing (NLP). Inspired by such significant achievements, some pioneering works have recently been done on employing…
Deep transfer learning recently has acquired significant research interest. It makes use of pre-trained models that are learned from a source domain, and utilizes these models for the tasks in a target domain. Model-based deep transfer…
This work explores the use of spatial context as a source of free and plentiful supervisory signal for training a rich visual representation. Given only a large, unlabeled image collection, we extract random pairs of patches from each image…
In deep learning, transfer learning (TL) has become the de facto approach when dealing with image related tasks. Visual features learnt for one task have been shown to be reusable for other tasks, improving performance significantly. By…
Transfer learning is a standard technique to improve performance on tasks with limited data. However, for medical imaging, the value of transfer learning is less clear. This is likely due to the large domain mismatch between the usual…