Related papers: Enhancing Representation Learning of EEG Data with…
Self-supervised audio representation learning offers an attractive alternative for obtaining generic audio embeddings, capable to be employed into various downstream tasks. Published approaches that consider both audio and words/tags…
We propose bootstrapped masked autoencoders (BootMAE), a new approach for vision BERT pretraining. BootMAE improves the original masked autoencoders (MAE) with two core designs: 1) momentum encoder that provides online feature as extra BERT…
Deep neural networks are powerful tools for biomedical image segmentation. These models are often trained with heavy supervision, relying on pairs of images and corresponding voxel-level labels. However, obtaining segmentations of…
The Masked autoencoder (MAE) has drawn attention as a representative self-supervised approach for masked image modeling with vision transformers. However, even though MAE shows better generalization capability than fully supervised training…
Recent years have seen remarkable progress in speech emotion recognition (SER), thanks to advances in deep learning techniques. However, the limited availability of labeled data remains a significant challenge in the field. Self-supervised…
The development of robust and generalisable models for encoding the spatio-temporal dynamics of human brain activity is crucial for advancing neuroscientific discoveries. However, significant individual variation in the organisation of the…
Pre-training by numerous image data has become de-facto for robust 2D representations. In contrast, due to the expensive data acquisition and annotation, a paucity of large-scale 3D datasets severely hinders the learning for high-quality 3D…
Cognitive load, the amount of mental effort required for task completion, plays an important role in performance and decision-making outcomes, making its classification and analysis essential in various sensitive domains. In this paper, we…
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 neural networks have been applied to audio spectrograms for respiratory sound classification, but it remains challenging to achieve satisfactory performance due to the scarcity of available data. Moreover, domain mismatch may be…
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…
In the field of medical image segmentation, challenges such as indistinct lesion features, ambiguous boundaries,and multi-scale characteristics have long revailed. This paper proposes an improved method named Intensity-Spatial Dual Masked…
Unsupervised learning is becoming more and more important recently. As one of its key components, the autoencoder (AE) aims to learn a latent feature representation of data which is more robust and discriminative. However, most AE based…
Transformer-based models attain excellent results and generalize well when trained on sufficient amounts of data. However, constrained by the limited data available in the audio domain, most transformer-based models for audio tasks are…
Deep auto-encoders (DAEs) have achieved great success in learning data representations via the powerful representability of neural networks. But most DAEs only focus on the most dominant structures which are able to reconstruct the data…
Pre-training strategies based on self-supervised learning (SSL) have proven to be effective pretext tasks for many downstream tasks in computer vision. Due to the significant disparity between medical and natural images, the application of…
Hyperspectral imagery provides rich spectral detail but poses unique challenges because of its high dimensionality in both spatial and spectral domains. We propose \textit{HyperspectralMAE}, a Transformer-based foundation model for…
Generalizing learned representations across significantly different visual domains is a fundamental yet crucial ability of the human visual system. While recent self-supervised learning methods have achieved good performances with…
Ultrasound imaging is one of the most widely used diagnostic modalities, offering real-time, radiation-free assessment across diverse clinical domains. However, interpretation of ultrasound images remains challenging due to high noise…
Masked image modeling is a promising self-supervised learning method for visual data. It is typically built upon image patches with random masks, which largely ignores the variation of information density between them. The question is: Is…