Related papers: MultiMAE Meets Earth Observation: Pre-training Mul…
Self-supervised pretraining on large-scale satellite data has raised great interest in building Earth observation (EO) foundation models. However, many important resources beyond pure satellite imagery, such as land-cover-land-use products…
Vision Transformers (ViTs) outperforms convolutional neural networks (CNNs) in several vision tasks with its global modeling capabilities. However, ViT lacks the inductive bias inherent to convolution making it require a large amount of…
Recent advancements in foundation models have significantly impacted various fields, including natural language processing, computer vision, and multi-modal tasks. One area that stands to benefit greatly is Earth observation, where these…
The unique complementarity of frame-based and event cameras for high frame rate object tracking has recently inspired some research attempts to develop multi-modal fusion approaches. However, these methods directly fuse both modalities and…
Masked autoencoder (MAE) is a promising self-supervised pre-training technique that can improve the representation learning of a neural network without human intervention. However, applying MAE directly to volumetric medical images poses…
Vision Transformers (ViT) become widely-adopted architectures for various vision tasks. Masked auto-encoding for feature pretraining and multi-scale hybrid convolution-transformer architectures can further unleash the potentials of ViT,…
Current Facial Action Unit (FAU) detection methods generally encounter difficulties due to the scarcity of labeled video training data and the limited number of training face IDs, which renders the trained feature extractor insufficient…
Self-supervised learning through masked autoencoders has attracted great attention for remote sensing (RS) foundation model (FM) development, enabling improved representation learning across diverse sensors and downstream tasks. However,…
Modern applications increasingly involve many heterogeneous input streams, such as clinical sensors, wearable device data, imaging, and text, each with distinct measurement models, sampling rates, and noise characteristics. We define this…
This work explores the effectiveness of masked image modelling for learning representations of retinal OCT images. To this end, we leverage Masked Autoencoders (MAE), a simple and scalable method for self-supervised learning, to obtain a…
Multimodal variational autoencoders have demonstrated their ability to learn the relationships between different modalities by mapping them into a latent representation. Their design and capacity to perform any-to-any conditional and…
Mixture-of-experts (MoE) architecture has been proven a powerful method for diverse tasks in training deep models in many applications. However, current MoE implementations are task agnostic, treating all tokens from different tasks in the…
Existing LiDAR-based 3D object detection methods for autonomous driving scenarios mainly adopt the training-from-scratch paradigm. Unfortunately, this paradigm heavily relies on large-scale labeled data, whose collection can be expensive…
Masked Autoencoders (MAEs) have emerged as a powerful pretraining technique for vision foundation models. Despite their effectiveness, they require extensive hyperparameter tuning (masking ratio, patch size, encoder/decoder layers) when…
Multi-view learning (MVL) leverages multiple sources or views of data to enhance machine learning model performance and robustness. This approach has been successfully used in the Earth Observation (EO) domain, where views have a…
We present a model that can perform multiple vision tasks and can be adapted to other downstream tasks efficiently. Despite considerable progress in multi-task learning, most efforts focus on learning from multi-label data: a single image…
Growing techniques have been emerging to improve the performance of passage retrieval. As an effective representation bottleneck pretraining technique, the contextual masked auto-encoder utilizes contextual embedding to assist in the…
The integration of multi-modal Magnetic Resonance Imaging (MRI) and clinical data holds great promise for enhancing the diagnosis of neurological disorders (NDs) in real-world clinical settings. Deep Learning (DL) has recently emerged as a…
Automated analysis of surgical videos is crucial for improving surgical training, workflow optimization, and postoperative assessment. We introduce a CSMAE, Masked Autoencoder (MAE)-based pretraining approach, specifically developed for…
Learning 3D representation plays a critical role in masked autoencoder (MAE) based pre-training methods for point cloud, including single-modal and cross-modal based MAE. Specifically, although cross-modal MAE methods learn strong 3D…