English
Related papers

Related papers: How to Understand Masked Autoencoders

200 papers

Intracranial aneurysms are a major cause of morbidity and mortality worldwide, and detecting them manually is a complex, time-consuming task. Albeit automated solutions are desirable, the limited availability of training data makes it…

Computer Vision and Pattern Recognition · Computer Science 2025-03-03 Alberto Mario Ceballos-Arroyo , Jisoo Kim , Chu-Hsuan Lin , Lei Qin , Geoffrey S. Young , Huaizu Jiang

The Masked autoencoder (MAE) has drawn attention as a representative self-supervised approach for masked image modeling with vision transformers. However, even though MAE shows better generalization capability than fully supervised training…

Computer Vision and Pattern Recognition · Computer Science 2024-05-29 Youngwan Lee , Jeffrey Ryan Willette , Jonghee Kim , Sung Ju Hwang

Masked Image Modeling (MIM) methods, like Masked Autoencoders (MAE), efficiently learn a rich representation of the input. However, for adapting to downstream tasks, they require a sufficient amount of labeled data since their rich features…

Computer Vision and Pattern Recognition · Computer Science 2023-09-15 Johannes Lehner , Benedikt Alkin , Andreas Fürst , Elisabeth Rumetshofer , Lukas Miklautz , Sepp Hochreiter

Recently, transformers have shown promising performance in learning graph representations. However, there are still some challenges when applying transformers to real-world scenarios due to the fact that deep transformers are hard to train…

Machine Learning · Computer Science 2022-05-13 Sixiao Zhang , Hongxu Chen , Haoran Yang , Xiangguo Sun , Philip S. Yu , Guandong Xu

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.…

Computer Vision and Pattern Recognition · Computer Science 2025-03-25 Hugo Chan-To-Hing , Bharadwaj Veeravalli

Recently, multi-modal masked autoencoders (MAE) has been introduced in 3D self-supervised learning, offering enhanced feature learning by leveraging both 2D and 3D data to capture richer cross-modal representations. However, these…

Computer Vision and Pattern Recognition · Computer Science 2025-07-29 Zhimin Chen , Xuewei Chen , Xiao Guo , Yingwei Li , Longlong Jing , Liang Yang , Bing Li

Current perception models in autonomous driving heavily rely on large-scale labelled 3D data, which is both costly and time-consuming to annotate. This work proposes a solution to reduce the dependence on labelled 3D training data by…

Computer Vision and Pattern Recognition · Computer Science 2023-10-10 Chen Min , Xinli Xu , Dawei Zhao , Liang Xiao , Yiming Nie , Bin Dai

Masked Autoencoders (MAEs) trained on audio spectrogram patches have emerged as a prominent approach for learning self-supervised audio representations. While several recent papers have evaluated key aspects of training MAEs on audio data,…

Sound · Computer Science 2025-07-15 Sarthak Yadav , Sergios Theodoridis , Zheng-Hua Tan

With the development of generative-based self-supervised learning (SSL) approaches like BeiT and MAE, how to learn good representations by masking random patches of the input image and reconstructing the missing information has grown in…

Computer Vision and Pattern Recognition · Computer Science 2022-08-02 Yabo Chen , Yuchen Liu , Dongsheng Jiang , Xiaopeng Zhang , Wenrui Dai , Hongkai Xiong , Qi Tian

The hematology analytics used for detection and classification of small blood components is a significant challenge. In particular, when objects exists as small pixel-sized entities in a large context of similar objects. Deep learning…

Computer Vision and Pattern Recognition · Computer Science 2026-02-10 H. Martin Gillis , Ming Hill , Paul Hollensen , Alan Fine , Thomas Trappenberg

Sparse autoencoders (SAEs) have emerged as a powerful tool for interpreting large language models (LLMs) by decomposing token activations into combinations of human-understandable features. While SAEs provide crucial insights into LLM…

Machine Learning · Computer Science 2025-11-11 Zhen Xu , Zhen Tan , Song Wang , Kaidi Xu , Tianlong Chen

Multiple modalities often co-occur when describing natural phenomena. Learning a joint representation of these modalities should yield deeper and more useful representations. Previous generative approaches to multi-modal input either do not…

Machine Learning · Computer Science 2018-11-13 Mike Wu , Noah Goodman

Neural network approaches to single-channel speech enhancement have received much recent attention. In particular, mask-based architectures have achieved significant performance improvements over conventional methods. This paper proposes a…

Audio and Speech Processing · Electrical Eng. & Systems 2023-09-22 Bengt J. Borgstrom , Michael S. Brandstein

Masked Autoencoders (MAEs) learn generalizable representations for image, text, audio, video, etc., by reconstructing masked input data from tokens of the visible data. Current MAE approaches for videos rely on random patch, tube, or…

Computer Vision and Pattern Recognition · Computer Science 2022-11-17 Wele Gedara Chaminda Bandara , Naman Patel , Ali Gholami , Mehdi Nikkhah , Motilal Agrawal , Vishal M. Patel

Masked point modeling methods have recently achieved great success in self-supervised learning for point cloud data. However, these methods are sensitive to rotations and often exhibit sharp performance drops when encountering rotational…

Computer Vision and Pattern Recognition · Computer Science 2024-12-30 Kunming Su , Qiuxia Wu , Panpan Cai , Xiaogang Zhu , Xuequan Lu , Zhiyong Wang , Kun Hu

Classical autoencoders are widely used to learn features of input data. To improve the feature learning, classical masked autoencoders extend classical autoencoders to learn the features of the original input sample in the presence of…

Quantum Physics · Physics 2026-05-01 Emma Andrews , Prabhat Mishra

This work contributes to breast cancer sub-type classification using histopathological images. We utilize masked autoencoders (MAEs) to learn a self-supervised embedding tailored for computer vision tasks in this domain. This embedding…

Computer Vision and Pattern Recognition · Computer Science 2025-06-10 Annalisa Chiocchetti , Marco Dossena , Christopher Irwin , Luigi Portinale

Contrastive learning (CL) for Vision Transformers (ViTs) in image domains has achieved performance comparable to CL for traditional convolutional backbones. However, in 3D point cloud pretraining with ViTs, masked autoencoder (MAE) modeling…

Computer Vision and Pattern Recognition · Computer Science 2024-07-09 Bin Ren , Guofeng Mei , Danda Pani Paudel , Weijie Wang , Yawei Li , Mengyuan Liu , Rita Cucchiara , Luc Van Gool , Nicu Sebe

Self-supervised learning excels in learning representations from large amounts of unlabeled data, demonstrating success across multiple data modalities. Yet, extending self-supervised learning to new modalities is non-trivial because the…

Machine Learning · Computer Science 2024-02-23 Johnathan Xie , Yoonho Lee , Annie S. Chen , Chelsea Finn

Building scalable models to learn from diverse, multimodal data remains an open challenge. For vision-language data, the dominant approaches are based on contrastive learning objectives that train a separate encoder for each modality. While…

Computer Vision and Pattern Recognition · Computer Science 2022-10-24 Xinyang Geng , Hao Liu , Lisa Lee , Dale Schuurmans , Sergey Levine , Pieter Abbeel