相关论文: SAR-W-MixMAE: SAR Foundation Model Training Using …

Masked Image Modeling has been one of the most popular self-supervised learning paradigms to learn representations from large-scale, unlabeled Earth Observation images. While incorporating multi-modal and multi-temporal Earth Observation…

Synthetic aperture radar (SAR) provides valuable information about the Earth's surface under all weather and illumination conditions. However, the inherent phenomenon of speckle and the presence of sidelobes around bright targets pose…

Recent advances in unsupervised learning have demonstrated the ability of large vision models to achieve promising results on downstream tasks by pre-training on large amount of unlabelled data. Such pre-training techniques have also been…

There has been a growing interest in using deep learning models for processing long surgical videos, in order to automatically detect clinical/operational activities and extract metrics that can enable workflow efficiency tools and…

This work aims to train Deep Learning models to perform Automatic Target Recognition (ATR) on Synthetic Aperture Radar (SAR) images. To circumvent the lack of real labelled measurements, we resort to synthetic data produced by SAR…

In this paper, we propose a simple yet powerful improvement over the recent Self-Supervised Audio Spectrogram Transformer (SSAST) model for speech and audio classification. Specifically, we leverage the insight that the SSAST uses a very…

Self-supervised learning has been a powerful training paradigm to facilitate representation learning. In this study, we design a masked autoencoder (MAE) to guide deep learning models to learn electroencephalography (EEG) signal…

Despite the progresses on pre-trained language models, there is a lack of unified frameworks for pre-trained sentence representation. As such, it calls for different pre-training methods for specific scenarios, and the pre-trained models…

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…

Current deep learning-based object detection for Synthetic Aperture Radar (SAR) imagery mainly adopts optical image methods, treating targets as texture patches while ignoring inherent electromagnetic scattering mechanisms. Though…

Masked image modeling (MIM) has become a popular strategy for self-supervised learning~(SSL) of visual representations with Vision Transformers. A representative MIM model, the masked auto-encoder (MAE), randomly masks a subset of image…

Sparse autoencoders (SAEs) are a popular method for interpreting concepts represented in large language model (LLM) activations. However, there is a lack of evidence regarding the validity of their interpretations due to the lack of a…

The growing Synthetic Aperture Radar (SAR) data has the potential to build a foundation model through Self-Supervised Learning (SSL) methods, which can achieve various SAR Automatic Target Recognition (ATR) tasks with pre-training in…

Masked Image Modeling (MIM) methods, like Masked Autoencoders (MAE), efficiently learn a rich representation of the input. However, for adapting to downstream tasks, they require a sufficient amount of labeled data since their rich features…

Large-scale self-supervised pre-training Transformer architecture have significantly boosted the performance for various tasks in natural language processing (NLP) and computer vision (CV). However, there is a lack of researches on…

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,…

Cross-modality magnetic resonance (MR) image synthesis can be used to generate missing modalities from given ones. Existing (supervised learning) methods often require a large number of paired multi-modal data to train an effective…

In the training of deep learning models, how the model parameters are initialized greatly affects the model performance, sample efficiency, and convergence speed. Representation learning for model initialization has recently been actively…

Recently, many foundation models for medical image analysis such as MedSAM, SwinUNETR have been released and proven to be useful in multiple tasks. However, considering the inherent heterogeneity and inhomogeneity of real-world medical…

In this paper, we propose Mixed and Masked AutoEncoder (MixMAE), a simple but efficient pretraining method that is applicable to various hierarchical Vision Transformers. Existing masked image modeling (MIM) methods for hierarchical Vision…