Related papers: DenoMAE2.0: Improving Denoising Masked Autoencoder…
The Linear Representation Hypothesis asserts that the embeddings learned by neural networks can be understood as linear combinations of features corresponding to high-level concepts. Based on this ansatz, sparse autoencoders (SAEs) have…
Self-supervised visual pre-training methods face an inherent tension: contrastive learning (CL) captures global semantics but loses fine-grained detail, while masked image modeling (MIM) preserves local textures but suffers from "attention…
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…
Whole-slide images are central to digital pathology, yet their extreme size and scarce annotations make self-supervised learning essential. Masked Autoencoders (MAEs) with Vision Transformer backbones have recently shown strong potential…
We propose an adaptive learning procedure to learn patch-based image priors for image denoising. The new algorithm, called the Expectation-Maximization (EM) adaptation, takes a generic prior learned from a generic external database and…
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…
Driven by improved architectures and better representation learning frameworks, the field of visual recognition has enjoyed rapid modernization and performance boost in the early 2020s. For example, modern ConvNets, represented by ConvNeXt,…
Denoising autoencoders (DAEs) have proven useful for unsupervised representation learning, but a thorough theoretical understanding is still lacking of how the input noise influences learning. Here we develop theory for how noise influences…
Applying Transformers to irregular time-series typically requires specializations to their baseline architecture, which can result in additional computational overhead and increased method complexity. We present the Rotary Masked…
Novelty detection is the task of recognizing samples that do not belong to the distribution of the target class. During training, the novelty class is absent, preventing the use of traditional classification approaches. Deep autoencoders…
In recent years, there are numerous works been proposed to leverage the techniques of deep learning to improve social-aware recommendation performance. In most cases, it requires a larger number of data to train a robust deep learning…
As a promising scheme of self-supervised learning, masked autoencoding has significantly advanced natural language processing and computer vision. Inspired by this, we propose a neat scheme of masked autoencoders for point cloud…
Synthetic Aperture Radar (SAR) target detection has long been impeded by inherent speckle noise and the prevalence of diminutive, ambiguous targets. While deep neural networks have advanced SAR target detection, their intrinsic…
With advancements of deep learning techniques, it is now possible to generate super-realistic images and videos, i.e., deepfakes. These deepfakes could reach mass audience and result in adverse impacts on our society. Although lots of…
Unsupervised feature extractors are known to perform an efficient and discriminative representation of data. Insight into the mappings they perform and human ability to understand them, however, remain very limited. This is especially…
Context-based detection methods such as DetectGPT achieve strong generalization in identifying AI-generated text by evaluating content compatibility with a model's learned distribution. In contrast, existing image detectors rely on…
This paper studies masked autoencoder (MAE) video pre-training for various temporal matching-based downstream tasks, i.e., object-level tracking tasks including video object tracking (VOT) and video object segmentation (VOS),…
For analysing real-world networks, graph representation learning is a popular tool. These methods, such as a graph autoencoder (GAE), typically rely on low-dimensional representations, also called embeddings, which are obtained through…
Denoising autoencoders (DAE) are trained to reconstruct their clean inputs with noise injected at the input level, while variational autoencoders (VAE) are trained with noise injected in their stochastic hidden layer, with a regularizer…
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…