English
Related papers

Related papers: Object-wise Masked Autoencoders for Fast Pre-train…

200 papers

Large, pretrained models are commonly finetuned with imagery that is heavily augmented to mimic different conditions and scales, with the resulting models used for various tasks with imagery from a range of spatial scales. Such models…

Computer Vision and Pattern Recognition · Computer Science 2023-09-25 Colorado J. Reed , Ritwik Gupta , Shufan Li , Sarah Brockman , Christopher Funk , Brian Clipp , Kurt Keutzer , Salvatore Candido , Matt Uyttendaele , Trevor Darrell

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

Strong gravitational lensing can reveal the influence of dark-matter substructure in galaxies, but analyzing these effects from noisy, low-resolution images poses a significant challenge. In this work, we propose a masked autoencoder (MAE)…

Masked autoencoding has become a successful pretraining paradigm for Transformer models for text, images, and, recently, point clouds. Raw automotive datasets are suitable candidates for self-supervised pre-training as they generally are…

Computer Vision and Pattern Recognition · Computer Science 2023-03-10 Georg Hess , Johan Jaxing , Elias Svensson , David Hagerman , Christoffer Petersson , Lennart Svensson

In this work, we explore self-supervised visual pre-training on images from diverse, in-the-wild videos for real-world robotic tasks. Like prior work, our visual representations are pre-trained via a masked autoencoder (MAE), frozen, and…

Robotics · Computer Science 2022-10-07 Ilija Radosavovic , Tete Xiao , Stephen James , Pieter Abbeel , Jitendra Malik , Trevor Darrell

With the exponential growth of multimedia data, leveraging multimodal sensors presents a promising approach for improving accuracy in human activity recognition. Nevertheless, accurately identifying these activities using both video data…

Computer Vision and Pattern Recognition · Computer Science 2024-08-09 Rex Liu , Xin Liu

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

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

Masked image modeling (MIM) has become a leading self-supervised learning strategy. MIMs such as Masked Autoencoder (MAE) learn strong representations by randomly masking input tokens for the encoder to process, with the decoder…

Computer Vision and Pattern Recognition · Computer Science 2024-08-27 Taekyung Kim , Sanghyuk Chun , Byeongho Heo , Dongyoon Han

This paper introduces self-taught object localization, a novel approach that leverages deep convolutional networks trained for whole-image recognition to localize objects in images without additional human supervision, i.e., without using…

Computer Vision and Pattern Recognition · Computer Science 2016-02-03 Loris Bazzani , Alessandro Bergamo , Dragomir Anguelov , Lorenzo Torresani

Vision Transformer (ViT) suffers from data scarcity in semi-supervised learning (SSL). To alleviate this issue, inspired by masked autoencoder (MAE), which is a data-efficient self-supervised learner, we propose Semi-MAE, a pure ViT-based…

Computer Vision and Pattern Recognition · Computer Science 2023-01-05 Haojie Yu , Kang Zhao , Xiaoming Xu

Self-supervised pretraining has transformed computer vision by enabling data-efficient fine-tuning, yet high-resolution training typically requires server-scale infrastructure, limiting in-domain foundation model development for many…

Computer Vision and Pattern Recognition · Computer Science 2026-02-19 David Smerkous , Zian Wang , Behzad Najafian

Mask-based pretraining has become a cornerstone of modern large-scale models across language, vision, and recently biology. Despite its empirical success, its role and limits in learning data representations have been unclear. In this work,…

Machine Learning · Computer Science 2025-09-29 Mingze Dong , Leda Wang , Yuval Kluger

Supervised (pre-)training currently yields state-of-the-art performance for representation learning for visual recognition, yet it comes at the cost of (1) intensive manual annotations and (2) an inherent restriction in the scope of data…

Computer Vision and Pattern Recognition · Computer Science 2016-12-05 Ruohan Gao , Dinesh Jayaraman , Kristen Grauman

There has been a growing interest in using deep learning models for processing long surgical videos, in order to automatically detect clinical/operational activities and extract metrics that can enable workflow efficiency tools and…

Computer Vision and Pattern Recognition · Computer Science 2023-05-22 Muhammad Abdullah Jamal , Omid Mohareri

Masked Autoencoder (MAE) is a notable method for self-supervised pretraining in visual representation learning. It operates by randomly masking image patches and reconstructing these masked patches using the unmasked ones. A key limitation…

Computer Vision and Pattern Recognition · Computer Science 2025-03-25 Han Guo , Ramtin Hosseini , Ruiyi Zhang , Sai Ashish Somayajula , Ranak Roy Chowdhury , Rajesh K. Gupta , Pengtao Xie

Perceptual understanding of the scene and the relationship between its different components is important for successful completion of robotic tasks. Representation learning has been shown to be a powerful technique for this, but most of the…

This paper studies masked autoencoder (MAE) video pre-training for various temporal matching-based downstream tasks, i.e., object-level tracking tasks including video object tracking (VOT) and video object segmentation (VOS),…

Computer Vision and Pattern Recognition · Computer Science 2025-04-07 Qiangqiang Wu , Tianyu Yang , Ziquan Liu , Wei Lin , Baoyuan Wu , Antoni B. Chan

This paper studies a conceptually simple extension of Masked Autoencoders (MAE) to spatiotemporal representation learning from videos. We randomly mask out spacetime patches in videos and learn an autoencoder to reconstruct them in pixels.…

Computer Vision and Pattern Recognition · Computer Science 2022-10-24 Christoph Feichtenhofer , Haoqi Fan , Yanghao Li , Kaiming He

This paper explores improvements to the masked image modeling (MIM) paradigm. The MIM paradigm enables the model to learn the main object features of the image by masking the input image and predicting the masked part by the unmasked part.…

Computer Vision and Pattern Recognition · Computer Science 2022-05-24 Jiawei Mao , Xuesong Yin , Yuanqi Chang , Honggu Zhou