Related papers: About Explicit Variance Minimization: Training Neu…

Vision Transformer(ViT) is one of the most widely used models in the computer vision field with its great performance on various tasks. In order to fully utilize the ViT-based architecture in various applications, proper visualization…

Transfer learning represents a recent paradigm shift in the way we build artificial intelligence (AI) systems. In contrast to training task-specific models, transfer learning involves pre-training deep learning models on a large corpus of…

We present a framework for learning multimodal representations from unlabeled data using convolution-free Transformer architectures. Specifically, our Video-Audio-Text Transformer (VATT) takes raw signals as inputs and extracts multimodal…

Adversarial Training (AT) and Virtual Adversarial Training (VAT) are the regularization techniques that train Deep Neural Networks (DNNs) with adversarial examples generated by adding small but worst-case perturbations to input examples. In…

Visual recognition models are not invariant to viewpoint changes in the 3D world, as different viewing directions can dramatically affect the predictions given the same object. Although many efforts have been devoted to making neural…

Self-supervised pre-training has become the priory choice to establish reliable neural networks for automated recognition of massive biomedical microscopy images, which are routinely annotation-free, without semantics, and without guarantee…

The quality of patient care associated with diagnostic radiology is proportionate to a physician workload. Segmentation is a fundamental limiting precursor to both diagnostic and therapeutic procedures. Advances in machine learning (ML) aim…

Due to the lack of quality annotation in medical imaging community, semi-supervised learning methods are highly valued in image semantic segmentation tasks. In this paper, an advanced consistency-aware pseudo-label-based self-ensembling…

The splendid success of convolutional neural networks (CNNs) in computer vision is largely attributable to the availability of massive annotated datasets, such as ImageNet and Places. However, in medical imaging, it is challenging to create…

Vision Transformers (ViTs) have gained significant popularity in the natural image domain but have been less successful in 3D medical image segmentation. Nevertheless, 3D ViTs are particularly interesting for large medical imaging volumes…

Variational Autoencoders (VAEs) have become a popular approach for dimensionality reduction. However, despite their ability to identify latent low-dimensional structures embedded within high-dimensional data, these latent representations…

Deep learning has transformed computer vision but relies heavily on large labeled datasets and computational resources. Transfer learning, particularly fine-tuning pretrained models, offers a practical alternative; however, models…

Self-supervised pretrain techniques have been widely used to improve the downstream tasks' performance. However, real-world magnetic resonance (MR) studies usually consist of different sets of contrasts due to different acquisition…

Conventional wisdom suggests that pre-training Vision Transformers (ViT) improves downstream performance by learning useful representations. Is this actually true? We investigate this question and find that the features and representations…

Supervised machine learning provides state-of-the-art solutions to a wide range of computer vision problems. However, the need for copious labelled training data limits the capabilities of these algorithms in scenarios where such input is…

Vision Transformer (ViT) models have achieved remarkable performance across various vision tasks, with scalability being a key advantage when applied to large datasets. This scalability enables ViT models to exhibit strong generalization…

Supervised learning has proved effective for medical image analysis. However, it can utilize only the small labeled portion of data; it fails to leverage the large amounts of unlabeled data that is often available in medical image datasets.…

Weakly supervised segmentation is an important problem in medical image analysis due to the high cost of pixelwise annotation. Prior methods, while often focusing on weak labels of 2D images, exploit few structural cues of volumetric…

Vision transformers (ViT) have been shown to allow for more flexible feature detection and can outperform convolutional neural network (CNN) when pre-trained on sufficient data. Due to their promising feature detection capabilities, we…

Few-shot video object segmentation aims to reduce annotation costs; however, existing methods still require abundant dense frame annotations for training, which are scarce in the medical domain. We investigate an extremely low-data regime…