Related papers: MAGMA: Manifold Regularization for MAEs
Self-supervised learning excels in learning representations from large amounts of unlabeled data, demonstrating success across multiple data modalities. Yet, extending self-supervised learning to new modalities is non-trivial because the…
Self-supervised learning (SSL) has become a popular method for generating invariant representations without the need for human annotations. Nonetheless, the desired invariant representation is achieved by utilising prior online…
The human voice is a promising non-invasive digital biomarker, yet deep learning for voice-based health analysis is hindered by data scarcity and domain mismatch, where models pre-trained on general audio fail to capture the subtle…
Pre-training has been an important ingredient in developing strong monocular depth estimation models in recent years. For instance, self-supervised learning (SSL) is particularly effective by alleviating the need for large datasets with…
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…
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…
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…
Model miscalibration has been frequently identified in modern deep neural networks. Recent work aims to improve model calibration directly through a differentiable calibration proxy. However, the calibration produced is often biased due to…
Masked autoencoders (MAE) have shown tremendous potential for self-supervised learning (SSL) in vision and beyond. However, point clouds from LiDARs used in automated driving are particularly challenging for MAEs since large areas of the 3D…
We investigated the adaptation and performance of Masked Autoencoders (MAEs) with Vision Transformer (ViT) architectures for self-supervised representation learning on one-dimensional (1D) ultrasound signals. Although MAEs have demonstrated…
Generative self-supervised learning (SSL), especially masked autoencoders, has become one of the most exciting learning paradigms and has shown great potential in handling graph data. However, real-world graphs are always heterogeneous,…
The supervised-learning-based morphing attack detection (MAD) solutions achieve outstanding success in dealing with attacks from known morphing techniques and known data sources. However, given variations in the morphing attacks, the…
Masked image modeling (MIM) has been recognized as a strong self-supervised pre-training approach in the vision domain. However, the mechanism and properties of the learned representations by such a scheme, as well as how to further enhance…
Recently, masked image modeling (MIM), an important self-supervised learning (SSL) method, has drawn attention for its effectiveness in learning data representation from unlabeled data. Numerous studies underscore the advantages of MIM,…
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…
Subtle hand differences make sign language recognition challenging, yet many existing methods rely on encoders pretrained on generic action datasets that poorly capture such fine-grained cues. We propose a self-supervised pretraining method…
Masked Autoencoders (MAE) achieve self-supervised learning of image representations by randomly removing a portion of visual tokens and reconstructing the original image as a pretext task, thereby significantly enhancing pretraining…
Deep learning has led to remarkable advances in computer vision. Even so, today's best models are brittle when presented with variations that differ even slightly from those seen during training. Minor shifts in the pose, color, or…
Network traffic classification using self-supervised pre-training models based on Masked Autoencoders (MAE) has demonstrated a huge potential. However, existing methods are confined to isolated byte-level reconstruction of individual flows,…
The coronavirus pandemic has been going on since the year 2019, and the trend is still not abating. Therefore, it is particularly important to classify medical CT scans to assist in medical diagnosis. At present, Supervised Deep Learning…