Related papers: WaveMAE: Wavelet decomposition Masked Auto-Encoder…

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…

Large, pretrained models are commonly finetuned with imagery that is heavily augmented to mimic different conditions and scales, with the resulting models used for various tasks with imagery from a range of spatial scales. Such models…

Masked autoencoder (MAE) is a promising self-supervised pre-training technique that can improve the representation learning of a neural network without human intervention. However, applying MAE directly to volumetric medical images poses…

This study explores the application of self-supervised learning (SSL) to the task of motion forecasting, an area that has not yet been extensively investigated despite the widespread success of SSL in computer vision and natural language…

Pretraining and fine-tuning have emerged as a new paradigm in remote sensing image interpretation. Among them, Masked Autoencoder (MAE)-based pretraining stands out for its strong capability to learn general feature representations via…

Recent advancements in foundation models have significantly impacted various fields, including natural language processing, computer vision, and multi-modal tasks. One area that stands to benefit greatly is Earth observation, where these…

Based on digital pathology slice scanning technology, artificial intelligence algorithms represented by deep learning have achieved remarkable results in the field of computational pathology. Compared to other medical images, pathology…

Hyperspectral satellite imagery offers sub-30 m views of Earth in hundreds of contiguous spectral bands, enabling fine-grained mapping of soils, crops, and land cover. While self-supervised Masked Autoencoders excel on RGB and low-band…

Building robust medical machine learning systems requires pretraining strategies that exploit the intrinsic structure present in clinical data. We introduce Multiview Masked Autoencoder (MVMAE), a self-supervised framework that leverages…

Fully supervised skeleton-based action recognition has achieved great progress with the blooming of deep learning techniques. However, these methods require sufficient labeled data which is not easy to obtain. In contrast, self-supervised…

Wireless goal-oriented semantic communication (GSC) has emerged as a promising paradigm by directly optimizing task performance. However, existing GSC frameworks typically operate on entire images and rely on labeled data for classification…

Self-supervised learning guided by masked image modelling, such as Masked AutoEncoder (MAE), has attracted wide attention for pretraining vision transformers in remote sensing. However, MAE tends to excessively focus on pixel details,…

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…

This paper explores Masked Autoencoders (MAE) with Gaussian Splatting. While reconstructive self-supervised learning frameworks such as MAE learns good semantic abstractions, it is not trained for explicit spatial awareness. Our approach,…

Vast amounts of remote sensing (RS) data provide Earth observations across multiple dimensions, encompassing critical spatial, temporal, and spectral information which is essential for addressing global-scale challenges such as land use…

Semantic segmentation of satellite imagery is crucial for Earth observation applications, but remains constrained by limited labelled training data. While self-supervised pretraining methods like Masked Autoencoders (MAE) have shown…

This paper introduces SenPa-MAE, a transformer architecture that encodes the sensor parameters of an observed multispectral signal into the image embeddings. SenPa-MAE can be pre-trained on imagery of different satellites with non-matching…

Self-supervised learning (SSL) enables learning useful inductive biases through utilizing pretext tasks that require no labels. The unlabeled nature of SSL makes it especially important for whole slide histopathological images (WSIs), where…

Weather forecasting is a long-standing computational challenge with direct societal and economic impacts. This task involves a large amount of continuous data collection and exhibits rich spatiotemporal dependencies over long periods,…

Latest federated learning (FL) methods started to focus on how to use unlabeled data in clients for training due to users' privacy concerns, high labeling costs, or lack of expertise. However, current Federated…