English
Related papers

Related papers: ExpPoint-MAE: Better interpretability and performa…

200 papers

Recent advances in self-supervised learning (SSL) have largely closed the gap with supervised ImageNet pretraining. Despite their success these methods have been primarily applied to unlabeled ImageNet images, and show marginal gains when…

Computer Vision and Pattern Recognition · Computer Science 2020-12-09 Ramprasaath R. Selvaraju , Karan Desai , Justin Johnson , Nikhil Naik

In this paper, we investigate self-supervised pre-training methods for document text recognition. Nowadays, large unlabeled datasets can be collected for many research tasks, including text recognition, but it is costly to annotate them.…

Computer Vision and Pattern Recognition · Computer Science 2024-05-02 Martin Kišš , Michal Hradiš

In this study, we investigated whether self-supervised pretraining could produce a neural network feature extractor applicable to multiple classification tasks in B-mode lung ultrasound analysis. When fine-tuning on three lung ultrasound…

Computer Vision and Pattern Recognition · Computer Science 2023-09-07 Blake VanBerlo , Brian Li , Jesse Hoey , Alexander Wong

In this paper, we study how the intrinsic nature of pre-training data contributes to the fine-tuned downstream performance. To this end, we pre-train different transformer-based masked language models on several corpora with certain…

Computation and Language · Computer Science 2020-12-23 Cheng-Han Chiang , Hung-yi Lee

Masked point modeling has become a promising scheme of self-supervised pre-training for point clouds. Existing methods reconstruct either the original points or related features as the objective of pre-training. However, considering the…

Computer Vision and Pattern Recognition · Computer Science 2023-09-26 Qibo Qiu , Honghui Yang , Wenxiao Wang , Shun Zhang , Haiming Gao , Haochao Ying , Wei Hua , Xiaofei He

This paper investigates the critical problem of representation similarity evolution during cross-domain transfer learning, with particular focus on understanding why pre-trained models maintain effectiveness when adapted to medical imaging…

Computer Vision and Pattern Recognition · Computer Science 2025-03-12 Wenqiang Zu , Shenghao Xie , Hao Chen , Lei Ma

No-reference point cloud quality assessment (NR-PCQA) aims to automatically predict the perceptual quality of point clouds without reference, which has achieved remarkable performance due to the utilization of deep learning-based models.…

Computer Vision and Pattern Recognition · Computer Science 2024-03-18 Ziyu Shan , Yujie Zhang , Qi Yang , Haichen Yang , Yiling Xu , Shan Liu

Pre-training strategies play a critical role in advancing the performance of transformer-based models for 3D point cloud tasks. In this paper, we introduce Point-RTD (Replaced Token Denoising), a novel pretraining strategy designed to…

Computer Vision and Pattern Recognition · Computer Science 2025-09-23 Gunner Stone , Youngsook Choi , Alireza Tavakkoli , Ankita Shukla

The significant effort required to annotate data for new training datasets hinders computer vision research and machine learning in the construction industry. This work explores adapting standard datasets and the latest transformer model…

Computer Vision and Pattern Recognition · Computer Science 2025-02-21 Lukas Rauch , Thomas Braml

Weather forecasting is a long-standing computational challenge with direct societal and economic impacts. This task involves a large amount of continuous data collection and exhibits rich spatiotemporal dependencies over long periods,…

Machine Learning · Computer Science 2023-12-18 Xin Man , Chenghong Zhang , Jin Feng , Changyu Li , Jie Shao

Self-supervised music foundation models underperform on key detection, which requires pitch-sensitive representations. In this work, we present the first systematic study showing that the design of self-supervised pretraining directly…

Sound · Computer Science 2026-04-14 Ori Yonay , Tracy Hammond , Tianbao Yang

Machine learning techniques in neutrino physics have traditionally relied on simulated data, which provides access to ground-truth labels. However, the accuracy of these simulations and the discrepancies between simulated and real data…

High Energy Physics - Experiment · Physics 2026-01-27 Felix J. Yu , Nicholas Kamp , Carlos A. Argüelles

Recent automated essay scoring (AES) studies increasingly use pretrained transformer models, but these models are usually pretrained on general-domain English and may under-represent second-language learner writing. This study investigates…

Computation and Language · Computer Science 2026-05-26 Duy Anh Nguyen

While originally designed for image generation, diffusion models have recently shown to provide excellent pretrained feature representations for semantic segmentation. Intrigued by this result, we set out to explore how well…

Computer Vision and Pattern Recognition · Computer Science 2023-07-06 Rui Gong , Martin Danelljan , Han Sun , Julio Delgado Mangas , Luc Van Gool

Recently self-supervised learning has been proposed in the field of human activity recognition as a solution to the labelled data availability problem. The idea being that by using pretext tasks such as reconstruction or contrastive…

Machine Learning · Computer Science 2023-07-04 Vitor Fortes Rey , Dominique Nshimyimana , Paul Lukowicz

We consider the problem of unsupervised domain adaptation for image classification. To learn target-domain-aware features from the unlabeled data, we create a self-supervised pretext task by augmenting the unlabeled data with a certain type…

Computer Vision and Pattern Recognition · Computer Science 2020-10-16 L. Xiao , J. Xu , D. Zhao , Z. Wang , L. Wang , Y. Nie , B. Dai

Pretraining on large labeled datasets is a prerequisite to achieve good performance in many computer vision tasks like 2D object recognition, video classification etc. However, pretraining is not widely used for 3D recognition tasks where…

Computer Vision and Pattern Recognition · Computer Science 2021-01-08 Zaiwei Zhang , Rohit Girdhar , Armand Joulin , Ishan Misra

Point cloud streaming is increasingly getting popular, evolving into the norm for interactive service delivery and the future Metaverse. However, the substantial volume of data associated with point clouds presents numerous challenges,…

Computer Vision and Pattern Recognition · Computer Science 2024-08-16 Yanlong Li , Chamara Madarasingha , Kanchana Thilakarathna

In practical machine learning settings, the data on which a model must make predictions often come from a different distribution than the data it was trained on. Here, we investigate the problem of unsupervised multi-source domain…

Machine Learning · Computer Science 2020-09-17 Dustin Wright , Isabelle Augenstein

Current popular backbones in computer vision, such as Vision Transformers (ViT) and ResNets are trained to perceive the world from 2D images. However, to more effectively understand 3D structural priors in 2D backbones, we propose Mask3D to…

Computer Vision and Pattern Recognition · Computer Science 2023-03-01 Ji Hou , Xiaoliang Dai , Zijian He , Angela Dai , Matthias Nießner