Related papers: Semi-Supervised Masked Autoencoders: Unlocking Vis…

In recent years, semi-supervised learning (SSL) has shown tremendous success in leveraging unlabeled data to improve the performance of deep learning models, which significantly reduces the demand for large amounts of labeled data. Many SSL…

Self-supervised learning (SSL) has recently emerged as a key strategy for building foundation models in remote sensing, where the scarcity of annotated data limits the applicability of fully supervised approaches. In this work, we introduce…

Advances in deep learning are re-defining how visual data is processed and understand by the machines. Vision Transformers (ViTs) have recently demonstrated prominent performance in computer vision related tasks. However, their performance…

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…

Vision-language models (VLMs) pre-trained on large, heterogeneous data sources are becoming increasingly popular, providing rich multi-modal embeddings that enable efficient transfer to new tasks. A particularly relevant application is…

Sparse Autoencoders (SAEs) have recently gained attention as a means to improve the interpretability and steerability of Large Language Models (LLMs), both of which are essential for AI safety. In this work, we extend the application of…

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…

Raman spectroscopy serves as a powerful and reliable tool for analyzing the chemical information of substances. The integration of Raman spectroscopy with deep learning methods enables rapid qualitative and quantitative analysis of…

Neuromorphic hardware equipped with learning capabilities can adapt to new, real-time data. While models of Spiking Neural Networks (SNNs) can now be trained using gradient descent to reach an accuracy comparable to equivalent conventional…

Semi-supervised learning is a challenging problem which aims to construct a model by learning from a limited number of labeled examples. Numerous methods have been proposed to tackle this problem, with most focusing on utilizing the…

Automated analysis of surgical videos is crucial for improving surgical training, workflow optimization, and postoperative assessment. We introduce a CSMAE, Masked Autoencoder (MAE)-based pretraining approach, specifically developed for…

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…

Generating semantic segmentation datasets has consistently been laborious and time-consuming, particularly in the context of large models or specialized domains(i.e. Medical Imaging or Remote Sensing). Specifically, large models necessitate…

We propose Masked Siamese Networks (MSN), a self-supervised learning framework for learning image representations. Our approach matches the representation of an image view containing randomly masked patches to the representation of the…

Image and language modeling is of crucial importance for vision-language pre-training (VLP), which aims to learn multi-modal representations from large-scale paired image-text data. However, we observe that most existing VLP methods focus…

The Vision Transformer (ViT) has demonstrated remarkable performance in Self-Supervised Learning (SSL) for 3D medical image analysis. Masked AutoEncoder (MAE) for feature pre-training can further unleash the potential of ViT on various…

Semi-supervised learning (SSL) has achieved significant progress by leveraging both labeled data and unlabeled data. Existing SSL methods overlook a common real-world scenario when labeled data is extremely scarce, potentially as limited as…

Self-Supervised Learning (SSL) has emerged as a key technique in machine learning, tackling challenges such as limited labeled data, high annotation costs, and variable wireless channel conditions. It is essential for developing Channel…

Unsupervised learning can leverage large-scale data sources without the need for annotations. In this context, deep learning-based autoencoders have shown great potential in detecting anomalies in medical images. However, especially…

Constructing large-scale labeled datasets for multi-modal perception model training in autonomous driving presents significant challenges. This has motivated the development of self-supervised pretraining strategies. However, existing…