Related papers: Beyond Labels: A Self-Supervised Framework with Ma…

Medical imaging tasks are very challenging due to the lack of publicly available labeled datasets. Hence, it is difficult to achieve high performance with existing deep-learning models as they require a massive labeled dataset to be trained…

Masked Autoencoders (MAEs) have emerged as a dominant strategy for self-supervised representation learning in natural images, where models are pre-trained to reconstruct masked patches with a pixel-wise mean squared error (MSE) between…

Ultrasound imaging is one of the most widely used diagnostic modalities, offering real-time, radiation-free assessment across diverse clinical domains. However, interpretation of ultrasound images remains challenging due to high noise…

The development of deep learning models in medical image analysis is majorly limited by the lack of large-sized and well-annotated datasets. Unsupervised learning does not require labels and is more suitable for solving medical image…

Medical image segmentation based on deep learning is often faced with the problems of insufficient datasets and long time-consuming labeling. In this paper, we introduce the self-supervised method MAE(Masked Autoencoders) into knee joint…

Variational autoencoders (VAEs) are widely used deep generative models capable of learning unsupervised latent representations of data. Such representations are often difficult to interpret or control. We consider the problem of…

Cancer is one of the deadliest diseases worldwide. Accurate diagnosis and classification of cancer subtypes are indispensable for effective clinical treatment. Promising results on automatic cancer subtyping systems have been published…

This work presents a novel self-supervised pre-training method to learn efficient representations without labels on histopathology medical images utilizing magnification factors. Other state-of-theart works mainly focus on fully supervised…

Masked Image Modeling (MIM)-based models, such as SdAE, CAE, GreenMIM, and MixAE, have explored different strategies to enhance the performance of Masked Autoencoders (MAE) by modifying prediction, loss functions, or incorporating…

Finding an interpretable non-redundant representation of real-world data is one of the key problems in Machine Learning. Biological neural networks are known to solve this problem quite well in unsupervised manner, yet unsupervised…

We address the challenge of training Vision Transformers (ViTs) when labeled data is scarce but unlabeled data is abundant. We propose Semi-Supervised Masked Autoencoder (SSMAE), a framework that jointly optimizes masked image…

The hematology analytics used for detection and classification of small blood components is a significant challenge. In particular, when objects exists as small pixel-sized entities in a large context of similar objects. Deep learning…

Unsupervised learning methods have become increasingly important in deep learning due to their demonstrated large utilization of datasets and higher accuracy in computer vision and natural language processing tasks. There is a growing trend…

Masked Autoencoders (MAEs) have been shown to be effective in pre-training Vision Transformers (ViTs) for natural and medical image analysis problems. By reconstructing missing pixel/voxel information in visible patches, a ViT encoder can…

Vision Transformer (ViT) suffers from data scarcity in semi-supervised learning (SSL). To alleviate this issue, inspired by masked autoencoder (MAE), which is a data-efficient self-supervised learner, we propose Semi-MAE, a pure ViT-based…

Unsupervised anomaly detection (UAD) presents a complementary alternative to supervised learning for brain tumor segmentation in magnetic resonance imaging (MRI), particularly when annotated datasets are limited, costly, or inconsistent. In…

Self-supervised learning excels in learning representations from large amounts of unlabeled data, demonstrating success across multiple data modalities. Yet, extending self-supervised learning to new modalities is non-trivial because the…

This paper shows that masked autoencoders (MAE) are scalable self-supervised learners for computer vision. Our MAE approach is simple: we mask random patches of the input image and reconstruct the missing pixels. It is based on two core…

We present a new flavor of Variational Autoencoder (VAE) that interpolates seamlessly between unsupervised, semi-supervised and fully supervised learning domains. We show that unlabeled datapoints not only boost unsupervised tasks, but also…

Masked Autoencoders (MAEs) achieve impressive performance in image classification tasks, yet the internal representations they learn remain less understood. This work started as an attempt to understand the strong downstream classification…