Related papers: VAMAE: Vessel-Aware Masked Autoencoders for OCT An…

Automated analysis of optical coherence tomography (OCT) and OCT angiography (OCTA) images is critical for robust ophthalmic diagnosis. Existing mainstream methods trained from scratch rely heavily on massive data and model scale, thereby…

Contrastive learning (CL) for Vision Transformers (ViTs) in image domains has achieved performance comparable to CL for traditional convolutional backbones. However, in 3D point cloud pretraining with ViTs, masked autoencoder (MAE) modeling…

In this work, we explore regions as a potential visual analogue of words for self-supervised image representation learning. Inspired by Masked Autoencoding (MAE), a generative pre-training baseline, we propose masked region autoencoding to…

Masked Autoencoding (MAE) has emerged as an effective approach for pre-training representations across multiple domains. In contrast to discrete tokens in natural languages, the input for image MAE is continuous and subject to additional…

Medical image segmentation remains a formidable challenge due to the label scarcity. Pre-training Vision Transformer (ViT) through masked image modeling (MIM) on large-scale unlabeled medical datasets presents a promising solution,…

Current video-based Masked Autoencoders (MAEs) primarily focus on learning effective spatiotemporal representations from a visual perspective, which may lead the model to prioritize general spatial-temporal patterns but often overlook…

Artificial Intelligence (AI) has the potential to revolutionize diagnosis and segmentation in medical imaging. However, development and clinical implementation face multiple challenges including limited data availability, lack of…

Unsupervised pre-training methods for large vision models have shown to enhance performance on downstream supervised tasks. Developing similar techniques for satellite imagery presents significant opportunities as unlabelled data is…

Masked image modeling is a promising self-supervised learning method for visual data. It is typically built upon image patches with random masks, which largely ignores the variation of information density between them. The question is: Is…

We introduce a novel masked graph autoencoder (MGAE) framework to perform effective learning on graph structure data. Taking insights from self-supervised learning, we randomly mask a large proportion of edges and try to reconstruct these…

To overcome the inherent domain gap between remote sensing (RS) images and natural images, some self-supervised representation learning methods have made promising progress. However, they have overlooked the diverse angles present in RS…

We propose MAE-SAM2, a novel foundation model for retinal vascular leakage segmentation on fluorescein angiography images. Due to the small size and dense distribution of the leakage areas, along with the limited availability of labeled…

Artificial intelligence (AI) classification holds promise as a novel and affordable screening tool for clinical management of ocular diseases. Rural and underserved areas, which suffer from lack of access to experienced ophthalmologists may…

Large-scale pre-training models have promoted the development of histopathology image analysis. However, existing self-supervised methods for histopathology images primarily focus on learning patch features, while there is a notable gap in…

Reliable automated analysis of Optical Coherence Tomography (OCT) imaging is crucial for diagnosing retinal disorders but faces a critical barrier: the need for expensive, labor-intensive expert annotations. Supervised deep learning models…

Accurate ocean mapping is essential for applications such as bathymetry estimation, seabed characterization, marine litter detection, and ecosystem monitoring. However, ocean remote sensing (RS) remains constrained by limited labeled data…

Multi-modal data in Earth Observation (EO) presents a huge opportunity for improving transfer learning capabilities when pre-training deep learning models. Unlike prior work that often overlooks multi-modal EO data, recent methods have…

Unsupervised anomaly detection (UAD) aims to find anomalous images by optimising a detector using a training set that contains only normal images. UAD approaches can be based on reconstruction methods, self-supervised approaches, and…

Learning representations from videos requires understanding continuous motion and visual correspondences between frames. In this paper, we introduce the Concatenated Masked Autoencoders (CatMAE) as a spatial-temporal learner for…

This paper tries to address a fundamental question in point cloud self-supervised learning: what is a good signal we should leverage to learn features from point clouds without annotations? To answer that, we introduce a point cloud…