Related papers: Multi-scale Transformer Network with Edge-aware Pr…

Many self-supervised learning methods are pre-trained on the well-curated ImageNet-1K dataset. In this work, given the excellent scalability of web data, we consider self-supervised pre-training on noisy web sourced image-text paired data.…

Unsupervised multimodal change detection is a practical and challenging topic that can play an important role in time-sensitive emergency applications. To address the challenge that multimodal remote sensing images cannot be directly…

Multimodal Magnetic Resonance (MR) Imaging plays a crucial role in disease diagnosis due to its ability to provide complementary information by analyzing a relationship between multimodal images on the same subject. Acquiring all MR…

We propose a deep mixture of multimodal hierarchical variational auto-encoders called MMHVAE that synthesizes missing images from observed images in different modalities. MMHVAE's design focuses on tackling four challenges: (i) creating a…

In recent years, MRI super-resolution techniques have achieved great success, especially multi-contrast methods that extract texture information from reference images to guide the super-resolution reconstruction. However, current methods…

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…

Unsupervised multivariate time series (MTS) representation learning aims to extract compact and informative representations from raw sequences without relying on labels, enabling efficient transfer to diverse downstream tasks. In this…

Recent advancements in large-scale Vision Transformers have made significant strides in improving pre-trained models for medical image segmentation. However, these methods face a notable challenge in acquiring a substantial amount of…

Image completion is the problem of generating whole images from fragments only. It encompasses inpainting (generating a patch given its surrounding), reverse inpainting/extrapolation (generating the periphery given the central patch) as…

Deep learning based medical image segmentation models usually require large datasets with high-quality dense segmentations to train, which are very time-consuming and expensive to prepare. One way to tackle this challenge is by using the…

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…

Increasingly many real world tasks involve data in multiple modalities or views. This has motivated the development of many effective algorithms for learning a common latent space to relate multiple domains. However, most existing…

Deep learning-based computer-aided diagnosis (CAD) of medical images requires large datasets. However, the lack of large publicly available labeled datasets limits the development of deep learning-based CAD systems. Generative Adversarial…

Multimodal pathological images are usually in clinical diagnosis, but computer vision-based multimodal image-assisted diagnosis faces challenges with modality fusion, especially in the absence of expert-annotated data. To achieve the…

Learning light-weight yet expressive deep networks in both image synthesis and image recognition remains a challenging problem. Inspired by a more recent observation that it is the data-specificity that makes the multi-head self-attention…

This paper shows that masked autoencoders (MAE) are scalable self-supervised learners for computer vision. Our MAE approach is simple: we mask random patches of the input image and reconstruct the missing pixels. It is based on two core…

For a complete comprehension of multi-person scenes, it is essential to go beyond basic tasks like detection and tracking. Higher-level tasks, such as understanding the interactions and social activities among individuals, are also crucial.…

"Masked Autoencoders (MAE) Are Scalable Vision Learners" revolutionizes the self-supervised learning method in that it not only achieves the state-of-the-art for image pre-training, but is also a milestone that bridges the gap between…

Unsupervised anomaly detection using only normal samples is of great significance for quality inspection in industrial manufacturing. Although existing reconstruction-based methods have achieved promising results, they still face two…

Multi-modal 3D understanding is a fundamental task in computer vision. Previous multi-modal fusion methods typically employ a single, dense fusion network, struggling to handle the significant heterogeneity and complexity across modalities,…