English
Related papers

Related papers: Test-Time Training with Masked Autoencoders

200 papers

Inspired by the masked language modeling (MLM) in natural language processing tasks, the masked image modeling (MIM) has been recognized as a strong self-supervised pre-training method in computer vision. However, the high random mask ratio…

Computer Vision and Pattern Recognition · Computer Science 2024-06-04 Zhaowen Li , Yousong Zhu , Zhiyang Chen , Wei Li , Chaoyang Zhao , Rui Zhao , Ming Tang , Jinqiao Wang

We address the problem of one-to-many mappings in supervised learning, where a single instance has many different solutions of possibly equal cost. The framework of conditional variational autoencoders describes a class of methods to tackle…

Machine Learning · Statistics 2019-09-11 Alexej Klushyn , Nutan Chen , Botond Cseke , Justin Bayer , Patrick van der Smagt

Test-time adaptation (TTA) aims to improve model generalizability when test data diverges from training distribution, offering the distinct advantage of not requiring access to training data and processes, especially valuable in the context…

Machine Learning · Computer Science 2024-02-28 Yige Yuan , Bingbing Xu , Liang Hou , Fei Sun , Huawei Shen , Xueqi Cheng

This paper presents SimVTP: a Simple Video-Text Pretraining framework via masked autoencoders. We randomly mask out the spatial-temporal tubes of input video and the word tokens of input text and then feed them into a unified autencoder to…

Computer Vision and Pattern Recognition · Computer Science 2022-12-08 Yue Ma , Tianyu Yang , Yin Shan , Xiu Li

A probability distribution allows practitioners to uncover hidden structure in the data and build models to solve supervised learning problems using limited data. The focus of this report is on Variational autoencoders, a method to learn…

Machine Learning · Computer Science 2022-06-22 Vasanth Kalingeri

We propose an approach for pre-training speech representations via a masked reconstruction loss. Our pre-trained encoder networks are bidirectional and can therefore be used directly in typical bidirectional speech recognition models. The…

Audio and Speech Processing · Electrical Eng. & Systems 2020-05-07 Weiran Wang , Qingming Tang , Karen Livescu

The incorporation of prior knowledge into learning is essential in achieving good performance based on small noisy samples. Such knowledge is often incorporated through the availability of related data arising from domains and tasks similar…

Machine Learning · Statistics 2026-02-24 Baruch Epstein , Ron Meir , Tomer Michaeli

The problem of end-to-end learning of a communication system using an autoencoder -- consisting of an encoder, channel, and decoder modeled using neural networks -- has recently been shown to be an effective approach. A challenge faced in…

Machine Learning · Computer Science 2023-03-07 Jayaram Raghuram , Yijing Zeng , Dolores García Martí , Rafael Ruiz Ortiz , Somesh Jha , Joerg Widmer , Suman Banerjee

We propose a generative model termed Deciphering Autoencoders. In this model, we assign a unique random dropout pattern to each data point in the training dataset and then train an autoencoder to reconstruct the corresponding data point…

Machine Learning · Computer Science 2024-07-01 Shunta Maeda

While scaling test-time compute can substantially improve model performance, existing approaches either rely on static compute allocation or sample from fixed generation distributions. In this work, we introduce a test-time compute…

Artificial Intelligence · Computer Science 2026-04-24 Bowen Zuo , Dongruo Zhou , Yinglun Zhu

Masked autoencoding has shown excellent performance on self-supervised video representation learning. Temporal redundancy has led to a high masking ratio and customized masking strategy in VideoMAE. In this paper, we aim to further improve…

Computer Vision and Pattern Recognition · Computer Science 2023-08-22 Bingkun Huang , Zhiyu Zhao , Guozhen Zhang , Yu Qiao , Limin Wang

Deep learning models often struggle under natural distribution shifts, a common challenge in real-world deployments. Test-Time Adaptation (TTA) addresses this by adapting models during inference without labeled source data. We present the…

Computer Vision and Pattern Recognition · Computer Science 2026-03-23 John Turnbull , Shivam Grover , Amin Jalali , Ali Etemad

Transformer-based models have delivered impressive results on many tasks, particularly vision and language tasks. In many model training situations, conventional configurations are typically adopted. For example, we often set the base model…

Machine Learning · Computer Science 2023-05-19 Fuzhao Xue , Jianghai Chen , Aixin Sun , Xiaozhe Ren , Zangwei Zheng , Xiaoxin He , Yongming Chen , Xin Jiang , Yang You

"Masked Autoencoders (MAE) Are Scalable Vision Learners" revolutionizes the self-supervised learning method in that it not only achieves the state-of-the-art for image pre-training, but is also a milestone that bridges the gap between…

Computer Vision and Pattern Recognition · Computer Science 2022-02-10 Shuhao Cao , Peng Xu , David A. Clifton

Currently, pre-trained language models (PLMs) do not cope well with the distribution shift problem, resulting in models trained on the training set failing in real test scenarios. To address this problem, the test-time adaptation (TTA)…

Computation and Language · Computer Science 2023-04-26 Yi Su , Yixin Ji , Juntao Li , Hai Ye , Min Zhang

Deep learning models have demonstrated exceptional performance across a wide range of computer vision tasks. However, their performance often degrades significantly when faced with distribution shifts, such as domain or dataset changes.…

Computer Vision and Pattern Recognition · Computer Science 2025-07-09 Samuel Barbeau , Pedram Fekri , David Osowiechi , Ali Bahri , Moslem Yazdanpanah , Masih Aminbeidokhti , Christian Desrosiers

Recent work has shown the importance of adaptation of broad-coverage contextualised embedding models on the domain of the target task of interest. Current self-supervised adaptation methods are simplistic, as the training signal comes from…

Computation and Language · Computer Science 2020-10-06 Thuy-Trang Vu , Dinh Phung , Gholamreza Haffari

In deep learning, maintaining model robustness against distribution shifts is critical. This work explores a broad range of possibilities to adapt vision-language foundation models at test-time, with a particular emphasis on CLIP and its…

Computer Vision and Pattern Recognition · Computer Science 2024-09-10 Mario Döbler , Robert A. Marsden , Tobias Raichle , Bin Yang

Deep Learning models have shown remarkable performance in a broad range of vision tasks. However, they are often vulnerable against domain shifts at test-time. Test-time training (TTT) methods have been developed in an attempt to mitigate…

Computer Vision and Pattern Recognition · Computer Science 2023-10-20 Gustavo A. Vargas Hakim , David Osowiechi , Mehrdad Noori , Milad Cheraghalikhani , Ismail Ben Ayed , Christian Desrosiers

Probabilistic forecasting of high dimensional multivariate time series is a notoriously challenging task, both in terms of computational burden and distribution modeling. Most previous work either makes simple distribution assumptions or…

Machine Learning · Computer Science 2021-01-27 Nam Nguyen , Brian Quanz