English
Related papers

Related papers: MultiMAE Meets Earth Observation: Pre-training Mul…

200 papers

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…

Computer Vision and Pattern Recognition · Computer Science 2024-09-25 Yi Wang , Conrad M Albrecht , Xiao Xiang Zhu

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…

Computer Vision and Pattern Recognition · Computer Science 2023-01-11 Jiawei Mao , Honggu Zhou , Xuesong Yin , Yuanqi Chang. Binling Nie. Rui Xu

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…

Computer Vision and Pattern Recognition · Computer Science 2024-10-21 Yohei Nakayama , Jiawei Su , Luis M. Pazos-Outón

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…

Computer Vision and Pattern Recognition · Computer Science 2024-11-05 Yucheng Chen , Lin Wang

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…

Computer Vision and Pattern Recognition · Computer Science 2023-08-24 Jia-Xin Zhuang , Luyang Luo , Hao Chen

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,…

Computer Vision and Pattern Recognition · Computer Science 2022-05-20 Peng Gao , Teli Ma , Hongsheng Li , Ziyi Lin , Jifeng Dai , Yu Qiao

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…

Computer Vision and Pattern Recognition · Computer Science 2024-07-17 Qiaoqiao Jin , Rui Shi , Yishun Dou , Bingbing Ni

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,…

Computer Vision and Pattern Recognition · Computer Science 2025-09-18 Leonard Hackel , Tom Burgert , Begüm Demir

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…

Machine Learning · Computer Science 2026-03-03 Xing Han , Hsing-Huan Chung , Joydeep Ghosh , Paul Pu Liang , Suchi Saria

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…

Computer Vision and Pattern Recognition · Computer Science 2024-05-24 Theodoros Pissas , Pablo Márquez-Neila , Sebastian Wolf , Martin Zinkernagel , Raphael Sznitman

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…

Machine Learning · Computer Science 2025-02-04 Daniel Wesego , Pedram Rooshenas

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…

Computation and Language · Computer Science 2023-10-26 Hai Pham , Young Jin Kim , Subhabrata Mukherjee , David P. Woodruff , Barnabas Poczos , Hany Hassan Awadalla

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…

Computer Vision and Pattern Recognition · Computer Science 2024-01-23 Zhiwei Lin , Yongtao Wang , Shengxiang Qi , Nan Dong , Ming-Hsuan Yang

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…

Computer Vision and Pattern Recognition · Computer Science 2025-08-25 Anthony Bisulco , Rahul Ramesh , Randall Balestriero , Pratik Chaudhari

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…

Machine Learning · Computer Science 2025-09-12 Francisco Mena , Diego Arenas , Andreas Dengel

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…

Computer Vision and Pattern Recognition · Computer Science 2023-06-30 Zitian Chen , Mingyu Ding , Yikang Shen , Wei Zhan , Masayoshi Tomizuka , Erik Learned-Miller , Chuang Gan

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…

Computation and Language · Computer Science 2023-04-07 Xing Wu , Guangyuan Ma , Peng Wang , Meng Lin , Zijia Lin , Fuzheng Zhang , Songlin Hu

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…

Image and Video Processing · Electrical Eng. & Systems 2025-06-19 Wajih Hassan Raza , Aamir Bader Shah , Yu Wen , Yidan Shen , Juan Diego Martinez Lemus , Mya Caryn Schiess , Timothy Michael Ellmore , Renjie Hu , Xin Fu

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…

Computer Vision and Pattern Recognition · Computer Science 2025-02-14 Nisarg A. Shah , Wele Gedara Chaminda Bandara , Shameema Skider , S. Swaroop Vedula , Vishal M. Patel

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…

Computer Vision and Pattern Recognition · Computer Science 2023-12-19 Yaohua Zha , Huizhen Ji , Jinmin Li , Rongsheng Li , Tao Dai , Bin Chen , Zhi Wang , Shu-Tao Xia