Related papers: $\mathsf{CSMAE~}$:~Cataract Surgical Masked Autoen…

Dense passage retrieval aims to retrieve the relevant passages of a query from a large corpus based on dense representations (i.e., vectors) of the query and the passages. Recent studies have explored improving pre-trained language models…

Masked autoencoders (MAE) have shown great promise in medical image classification. However, the random masking strategy employed by traditional MAEs may overlook critical areas in medical images, where even subtle changes can indicate…

Compressed sensing magnetic resonance imaging (CS-MRI) seeks to recover visual information from subsampled measurements for diagnostic tasks. Traditional CS-MRI methods often separately address measurement subsampling, image reconstruction,…

The use of self-supervised pre-training has emerged as a promising approach to enhance the performance of many different visual tasks. In this context, recent approaches have employed the Masked Image Modeling paradigm, which pre-trains a…

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…

Recently, significant progress has been made in masked image modeling to catch up to masked language modeling. However, unlike words in NLP, the lack of semantic decomposition of images still makes masked autoencoding (MAE) different…

Human Action Recognition using WiFi Channel State Information (CSI) has emerged as an attractive alternative to vision-based methods due to its ubiquity, device-agnostic nature, and inherent privacy-preserving capabilities. However, the…

We are interested in learning scalable agents for reinforcement learning that can learn from large-scale, diverse sequential data similar to current large vision and language models. To this end, this paper presents masked decision…

Redshift prediction is a fundamental task in astronomy, essential for understanding the expansion of the universe and determining the distances of astronomical objects. Accurate redshift prediction plays a crucial role in advancing our…

This paper revisits the standard pretrain-then-finetune paradigm used in computer vision for visual recognition tasks. Typically, state-of-the-art foundation models are pretrained using large scale (weakly) supervised datasets with billions…

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…

Learning high-quality video representation has shown significant applications in computer vision and remains challenging. Previous work based on mask autoencoders such as ImageMAE and VideoMAE has proven the effectiveness of learning…

Federated learning is a specific distributed learning paradigm in which a central server aggregates updates from multiple clients' local models, thereby enabling the server to learn without requiring clients to upload their private data,…

This work contributes to breast cancer sub-type classification using histopathological images. We utilize masked autoencoders (MAEs) to learn a self-supervised embedding tailored for computer vision tasks in this domain. This embedding…

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…

Despite pre-training's progress in many important NLP tasks, it remains to explore effective pre-training strategies for dense retrieval. In this paper, we propose RetroMAE, a new retrieval oriented pre-training paradigm based on Masked…

To better support information retrieval tasks such as web search and open-domain question answering, growing effort is made to develop retrieval-oriented language models, e.g., RetroMAE and many others. Most of the existing works focus on…

Real-time video understanding is critical to guide procedures in minimally invasive surgery (MIS). However, supervised learning approaches require large, annotated datasets that are scarce due to annotation efforts that are prohibitive,…

We propose a masked self-supervised learning framework, called BRepMAE, for automatically extracting a valuable representation of the input computer-aided design (CAD) model to recognize its machining features. Representation learning is…

Distributed fiber-optic acoustic sensing (DAS) has emerged as a transformative approach for distributed vibration measurement with high spatial resolution and long measurement range while maintaining cost-efficiency. However, the…