Related papers: Mixed Autoencoder for Self-supervised Visual Repre…

Masked autoencoders (MAEs) have emerged as a powerful approach for pre-training on unlabelled data, capable of learning robust and informative feature representations. This is particularly advantageous in diffused lung disease research,…

Most existing methods for unsupervised industrial anomaly detection train a separate model for each object category. This kind of approach can easily capture the category-specific feature distributions, but results in high storage cost and…

Masked Autoencoders learn strong visual representations and achieve state-of-the-art results in several independent modalities, yet very few works have addressed their capabilities in multi-modality settings. In this work, we focus on point…

Broadcast and media organizations increasingly rely on artificial intelligence to automate the labor-intensive processes of content indexing, tagging, and metadata generation. However, existing AI systems typically operate on a single…

Self-supervised pre-training for images without labels has recently achieved promising performance in image classification. The success of transformer-based methods, ViT and MAE, draws the community's attention to the design of backbone…

Learning robust representations across extremely heterogeneous modalities remains a fundamental challenge in multi-modal vision. As a critical and profound instantiation of this challenge, high-resolution (HR) joint optical and synthetic…

Many recent inpainting works have achieved impressive results by leveraging Deep Neural Networks (DNNs) to model various prior information for image restoration. Unfortunately, the performance of these methods is largely limited by the…

Masked image modeling (MIM) as pre-training is shown to be effective for numerous vision downstream tasks, but how and where MIM works remain unclear. In this paper, we compare MIM with the long-dominant supervised pre-trained models from…

Learning disentangled representation from any unlabelled data is a non-trivial problem. In this paper we propose Information Maximising Autoencoder (InfoAE) where the encoder learns powerful disentangled representation through maximizing…

Existing Masked Image Modeling (MIM) depends on a spatial patch-based masking-reconstruction strategy to perceive objects'features from unlabeled images, which may face two limitations when applied to chest CT: 1) inefficient feature…

Self-supervised frameworks for representation learning have recently stirred up interest among the remote sensing community, given their potential to mitigate the high labeling costs associated with curating large satellite image datasets.…

Learning interpretable and disentangled representations of data is a key topic in machine learning research. Variational Autoencoder (VAE) is a scalable method for learning directed latent variable models of complex data. It employs a clear…

Masked AutoEncoder (MAE) has recently led the trends of visual self-supervision area by an elegant asymmetric encoder-decoder design, which significantly optimizes both the pre-training efficiency and fine-tuning accuracy. Notably, the…

At the most basic level, pixels are the source of the visual information through which we perceive the world. Pixels contain information at all levels, ranging from low-level attributes to high-level concepts. Autoencoders represent a…

Multivariate Time Series forecasting has been an increasingly popular topic in various applications and scenarios. Recently, contrastive learning and Transformer-based models have achieved good performance in many long-term series…

Finding an interpretable non-redundant representation of real-world data is one of the key problems in Machine Learning. Biological neural networks are known to solve this problem quite well in unsupervised manner, yet unsupervised…

Deep neural networks have achieved remarkable progress in enhancing low-light images by improving their brightness and eliminating noise. However, most existing methods construct end-to-end mapping networks heuristically, neglecting the…

The volume of unlabelled Earth observation (EO) data is huge, but many important applications lack labelled training data. However, EO data offers the unique opportunity to pair data from different modalities and sensors automatically based…

Clustering high-dimensional data, such as images or biological measurements, is a long-standingproblem and has been studied extensively. Recently, Deep Clustering has gained popularity due toits flexibility in fitting the specific…

Image and language modeling is of crucial importance for vision-language pre-training (VLP), which aims to learn multi-modal representations from large-scale paired image-text data. However, we observe that most existing VLP methods focus…