English
Related papers

Related papers: How to Understand Masked Autoencoders

200 papers

Self-supervised learning guided by masked image modelling, such as Masked AutoEncoder (MAE), has attracted wide attention for pretraining vision transformers in remote sensing. However, MAE tends to excessively focus on pixel details,…

Computer Vision and Pattern Recognition · Computer Science 2023-10-31 Yi Wang , Hugo Hernández Hernández , Conrad M Albrecht , Xiao Xiang Zhu

Generalizing learned representations across significantly different visual domains is a fundamental yet crucial ability of the human visual system. While recent self-supervised learning methods have achieved good performances with…

Computer Vision and Pattern Recognition · Computer Science 2022-06-07 Haiyang Yang , Meilin Chen , Yizhou Wang , Shixiang Tang , Feng Zhu , Lei Bai , Rui Zhao , Wanli Ouyang

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…

Computer Vision and Pattern Recognition · Computer Science 2022-03-29 Yatian Pang , Wenxiao Wang , Francis E. H. Tay , Wei Liu , Yonghong Tian , Li Yuan

Remote sensing images present unique challenges to image analysis due to the extensive geographic coverage, hardware limitations, and misaligned multi-scale images. This paper revisits the classical multi-scale representation learning…

Computer Vision and Pattern Recognition · Computer Science 2026-04-03 Maofeng Tang , Andrei Cozma , Konstantinos Georgiou , Hairong Qi

Self-Supervised Learning (SSL) has emerged as a key technique in machine learning, tackling challenges such as limited labeled data, high annotation costs, and variable wireless channel conditions. It is essential for developing Channel…

Signal Processing · Electrical Eng. & Systems 2026-01-08 Jun Jiang , Xiaolong Ruan , Shugong Xu

Dynamic facial expression recognition (DFER) is essential to the development of intelligent and empathetic machines. Prior efforts in this field mainly fall into supervised learning paradigm, which is severely restricted by the limited…

Computer Vision and Pattern Recognition · Computer Science 2023-08-09 Licai Sun , Zheng Lian , Bin Liu , Jianhua Tao

We propose the Motion Capsule Autoencoder (MCAE), which addresses a key challenge in the unsupervised learning of motion representations: transformation invariance. MCAE models motion in a two-level hierarchy. In the lower level, a…

Computer Vision and Pattern Recognition · Computer Science 2021-10-04 Ziwei Xu , Xudong Shen , Yongkang Wong , Mohan S Kankanhalli

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…

Computer Vision and Pattern Recognition · Computer Science 2022-05-23 Xiang Li , Wenhai Wang , Lingfeng Yang , Jian Yang

Pre-training by numerous image data has become de-facto for robust 2D representations. In contrast, due to the expensive data acquisition and annotation, a paucity of large-scale 3D datasets severely hinders the learning for high-quality 3D…

Computer Vision and Pattern Recognition · Computer Science 2022-12-14 Renrui Zhang , Liuhui Wang , Yu Qiao , Peng Gao , Hongsheng Li

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…

Machine Learning · Computer Science 2023-01-24 Zhe Li , Zhongwen Rao , Lujia Pan , Pengyun Wang , Zenglin Xu

In this work, we propose a Multi-Window Masked Autoencoder (MW-MAE) fitted with a novel Multi-Window Multi-Head Attention (MW-MHA) module that facilitates the modelling of local-global interactions in every decoder transformer block through…

Sound · Computer Science 2023-10-03 Sarthak Yadav , Sergios Theodoridis , Lars Kai Hansen , Zheng-Hua Tan

Image and video restoration has achieved a remarkable leap with the advent of deep learning. The success of deep learning paradigm lies in three key components: data, model, and loss. Currently, many efforts have been devoted to the first…

Computer Vision and Pattern Recognition · Computer Science 2023-03-30 Man Zhou , Naishan Zheng , Jie Huang , Chunle Guo , Chongyi Li

Network traffic classification using self-supervised pre-training models based on Masked Autoencoders (MAE) has demonstrated a huge potential. However, existing methods are confined to isolated byte-level reconstruction of individual flows,…

Cryptography and Security · Computer Science 2026-04-01 Xiao Liu , Xiaowei Fu , Fuxiang Huang , Lei Zhang

We are interested in learning scalable agents for reinforcement learning that can learn from large-scale, diverse sequential data similar to current large vision and language models. To this end, this paper presents masked decision…

Machine Learning · Computer Science 2023-05-30 Fangchen Liu , Hao Liu , Aditya Grover , Pieter Abbeel

Medical image segmentation remains a formidable challenge due to the label scarcity. Pre-training Vision Transformer (ViT) through masked image modeling (MIM) on large-scale unlabeled medical datasets presents a promising solution,…

Computer Vision and Pattern Recognition · Computer Science 2025-02-13 Fenghe Tang , Qingsong Yao , Wenxin Ma , Chenxu Wu , Zihang Jiang , S. Kevin Zhou

Learning aligned multimodal embeddings from weakly paired, label-free corpora is challenging: pipelines often provide only pre-extracted features, clips contain multiple events, and spurious co-occurrences. We propose HSC-MAE (Hierarchical…

Multimedia · Computer Science 2026-04-07 Donghuo Zeng , Hao Niu , Masato Taya

Recent advances in latent diffusion models have demonstrated their effectiveness for high-resolution image synthesis. However, the properties of the latent space from tokenizer for better learning and generation of diffusion models remain…

Computer Vision and Pattern Recognition · Computer Science 2025-06-02 Hao Chen , Yujin Han , Fangyi Chen , Xiang Li , Yidong Wang , Jindong Wang , Ze Wang , Zicheng Liu , Difan Zou , Bhiksha Raj

Bioacoustic recognition requires fine-grained acoustic understanding to distinguish similar-sounding species. However, many large-scale data repositories such as iNaturalist are weakly annotated, often with only a single positive species…

Sound · Computer Science 2026-05-15 Wuao Liu , Mustafa Chasmai , Subhransu Maji , Grant Van Horn

Pre-training strategies based on self-supervised learning (SSL) have proven to be effective pretext tasks for many downstream tasks in computer vision. Due to the significant disparity between medical and natural images, the application of…

Recent speech modeling relies on explicit attributes such as pitch, content, and speaker identity, but these alone cannot capture the full richness of natural speech. We introduce RT-MAE, a novel masked autoencoder framework that augments…

Sound · Computer Science 2026-01-28 Samir Sadok , Stéphane Lathuilière , Xavier Alameda-Pineda