English
Related papers

Related papers: Rethinking Patch Dependence for Masked Autoencoder…

200 papers

Masked autoencoders (MAEs) have emerged recently as art self-supervised spatiotemporal representation learners. Inheriting from the image counterparts, however, existing video MAEs still focus largely on static appearance learning whilst…

Computer Vision and Pattern Recognition · Computer Science 2022-10-11 Haosen Yang , Deng Huang , Bin Wen , Jiannan Wu , Hongxun Yao , Yi Jiang , Xiatian Zhu , Zehuan Yuan

Recent general-purpose audio representations show state-of-the-art performance on various audio tasks. These representations are pre-trained by self-supervised learning methods that create training signals from the input. For example,…

Audio and Speech Processing · Electrical Eng. & Systems 2023-03-09 Daisuke Niizumi , Daiki Takeuchi , Yasunori Ohishi , Noboru Harada , Kunio Kashino

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

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

Masked AutoEncoders (MAE) have emerged as a robust self-supervised framework, offering remarkable performance across a wide range of downstream tasks. To increase the difficulty of the pretext task and learn richer visual representations,…

Computer Vision and Pattern Recognition · Computer Science 2024-07-19 Carlos Hinojosa , Shuming Liu , Bernard Ghanem

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

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

Many recent inpainting works have achieved impressive results by leveraging Deep Neural Networks (DNNs) to model various prior information for image restoration. Unfortunately, the performance of these methods is largely limited by the…

Computer Vision and Pattern Recognition · Computer Science 2023-08-29 Chenjie Cao , Qiaole Dong , Yanwei Fu

The last years have witnessed the emergence of a promising self-supervised learning strategy, referred to as masked autoencoding. However, there is a lack of theoretical understanding of how masking matters on graph autoencoders (GAEs). In…

Machine Learning · Computer Science 2023-05-30 Jintang Li , Ruofan Wu , Wangbin Sun , Liang Chen , Sheng Tian , Liang Zhu , Changhua Meng , Zibin Zheng , Weiqiang Wang

Transformer-based Self-supervised Representation Learning methods learn generic features from unlabeled datasets for providing useful network initialization parameters for downstream tasks. Recently, self-supervised learning based upon…

Computer Vision and Pattern Recognition · Computer Science 2023-09-12 Jincen Jiang , Xuequan Lu , Lizhi Zhao , Richard Dazeley , Meili Wang

Masked autoencoder (MAE), a simple and effective self-supervised learning framework based on the reconstruction of masked image regions, has recently achieved prominent success in a variety of vision tasks. Despite the emergence of…

Machine Learning · Computer Science 2023-06-09 Lingjing Kong , Martin Q. Ma , Guangyi Chen , Eric P. Xing , Yuejie Chi , Louis-Philippe Morency , Kun Zhang

Transformers have shown significant effectiveness for various vision tasks including both high-level vision and low-level vision. Recently, masked autoencoders (MAE) for feature pre-training have further unleashed the potential of…

Computer Vision and Pattern Recognition · Computer Science 2023-03-31 Huiyu Duan , Wei Shen , Xiongkuo Min , Danyang Tu , Long Teng , Jia Wang , Guangtao Zhai

Current video-based Masked Autoencoders (MAEs) primarily focus on learning effective spatiotemporal representations from a visual perspective, which may lead the model to prioritize general spatial-temporal patterns but often overlook…

Computer Vision and Pattern Recognition · Computer Science 2025-02-13 Shihab Aaqil Ahamed , Malitha Gunawardhana , Liel David , Michael Sidorov , Daniel Harari , Muhammad Haris Khan

Masked Autoencoding (MAE) has emerged as an effective approach for pre-training representations across multiple domains. In contrast to discrete tokens in natural languages, the input for image MAE is continuous and subject to additional…

Computer Vision and Pattern Recognition · Computer Science 2022-10-14 Ronghang Hu , Shoubhik Debnath , Saining Xie , Xinlei Chen

Masked Autoencoders (MAEs) have emerged as a dominant strategy for self-supervised representation learning in natural images, where models are pre-trained to reconstruct masked patches with a pixel-wise mean squared error (MSE) between…

Image and Video Processing · Electrical Eng. & Systems 2025-07-16 Chetan Madan , Aarjav Satia , Soumen Basu , Pankaj Gupta , Usha Dutta , Chetan Arora

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

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…

Computer Vision and Pattern Recognition · Computer Science 2017-11-17 Tanmoy Mukherjee , Makoto Yamada , Timothy M. Hospedales

We present an extension to masked autoencoders (MAE) which improves on the representations learnt by the model by explicitly encouraging the learning of higher scene-level features. We do this by: (i) the introduction of a perceptual…

Computer Vision and Pattern Recognition · Computer Science 2023-03-29 Samyakh Tukra , Frederick Hoffman , Ken Chatfield

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.…

Computer Vision and Pattern Recognition · Computer Science 2024-04-09 Mahsa Ehsanpour , Ian Reid , Hamid Rezatofighi

Masked Autoencoders (MAEs) have been shown to be effective in pre-training Vision Transformers (ViTs) for natural and medical image analysis problems. By reconstructing missing pixel/voxel information in visible patches, a ViT encoder can…

Computer Vision and Pattern Recognition · Computer Science 2025-11-20 Pengfei Gu , Huimin Li , Yejia Zhang , Chaoli Wang , Danny Z. Chen