English
Related papers

Related papers: DAS-MAE: A self-supervised pre-training framework …

200 papers

Pre-training strategies based on self-supervised learning (SSL) have proven to be effective pretext tasks for many downstream tasks in computer vision. Due to the significant disparity between medical and natural images, the application of…

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

Universal sound separation (USS) is a task of separating mixtures of arbitrary sound sources. Typically, universal separation models are trained from scratch in a supervised manner, using labeled data. Self-supervised learning (SSL) is an…

Audio and Speech Processing · Electrical Eng. & Systems 2024-11-07 Junqi Zhao , Xubo Liu , Jinzheng Zhao , Yi Yuan , Qiuqiang Kong , Mark D. Plumbley , Wenwu Wang

Sound event detection (SED) methods that leverage a large pre-trained Transformer encoder network have shown promising performance in recent DCASE challenges. However, they still rely on an RNN-based context network to model temporal…

Sound · Computer Science 2024-08-20 Pengfei Cai , Yan Song , Kang Li , Haoyu Song , Ian McLoughlin

Speech representation learning approaches for non-semantic tasks such as language recognition have either explored supervised embedding extraction methods using a classifier model or self-supervised representation learning approaches using…

Computation and Language · Computer Science 2023-06-08 Shikhar Vashishth , Shikhar Bharadwaj , Sriram Ganapathy , Ankur Bapna , Min Ma , Wei Han , Vera Axelrod , Partha Talukdar

Masked autoencoders (MAEs) have emerged as a powerful approach for pre-training on unlabelled data, capable of learning robust and informative feature representations. This is particularly advantageous in diffused lung disease research,…

Self-supervised models allow (pre-)training on unlabeled data and therefore have the potential to overcome the need for large annotated cohorts. One leading self-supervised model is the masked autoencoder (MAE) which was developed on…

Image and Video Processing · Electrical Eng. & Systems 2023-03-13 Daniel M. Lang , Eli Schwartz , Cosmin I. Bercea , Raja Giryes , Julia A. Schnabel

In extreme scenarios such as nighttime or low-visibility environments, achieving reliable perception is critical for applications like autonomous driving, robotics, and surveillance. Multi-modality image fusion, particularly integrating…

Computer Vision and Pattern Recognition · Computer Science 2025-05-27 Yuchen Guo , Ruoxiang Xu , Rongcheng Li , Weifeng Su

In this paper, we propose to pre-train audio encoders using synthetic patterns instead of real audio data. Our proposed framework consists of two key elements. The first one is Masked Autoencoder (MAE), a self-supervised learning framework…

Audio and Speech Processing · Electrical Eng. & Systems 2024-10-02 Yuchi Ishikawa , Tatsuya Komatsu , Yoshimitsu Aoki

Intelligent behaviour in the real-world requires the ability to acquire new knowledge from an ongoing sequence of experiences while preserving and reusing past knowledge. We propose a novel algorithm for unsupervised representation learning…

Diffusion autoencoders (DAEs) are typically formulated as a noise prediction model and trained with a linear-$\beta$ noise schedule that spends much of its sampling steps at high noise levels. Because high noise levels are associated with…

Computer Vision and Pattern Recognition · Computer Science 2025-05-01 Pramook Khungurn , Sukit Seripanitkarn , Phonphrm Thawatdamrongkit , Supasorn Suwajanakorn

Models of acoustic word embeddings (AWEs) learn to map variable-length spoken word segments onto fixed-dimensionality vector representations such that different acoustic exemplars of the same word are projected nearby in the embedding…

Computation and Language · Computer Science 2022-09-20 Badr M. Abdullah , Bernd Möbius , Dietrich Klakow

The detection of underwater targets is severely affected by the non-uniform spatial characteristics of marine environmental noise. Additionally, the presence of both natural and anthropogenic acoustic sources, including shipping traffic,…

Signal Processing · Electrical Eng. & Systems 2025-12-15 Siyuan Cang , Cong Liu , Xueli Sheng , Xiaoming Cui , Chao Li , Changxin Fa , Jiantong Chen , Chaoran Yang , Huayong Yang

Self-supervised pre-training paradigm has gained increasing prominence for learning transferable representations in medical imaging, yet existing methods for ultrasound (US) images operate at the image or frame level, overlooking the…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Chunzheng Zhu , Yijun Wang , Jianxin Lin , Feng Wang , Hongwei Wang , Lei Zhao , Shengli Li , Kenli Li

Learning from electronic health records (EHRs) time series is challenging due to irregular sam- pling, heterogeneous missingness, and the resulting sparsity of observations. Prior self-supervised meth- ods either impute before learning,…

Machine Learning · Computer Science 2026-02-18 Xiao Xiang , David Restrepo , Hyewon Jeong , Yugang Jia , Leo Anthony Celi

Domain Generalization (DG), designed to enhance out-of-distribution (OOD) generalization, is all about learning invariance against domain shifts utilizing sufficient supervision signals. Yet, the scarcity of such labeled data has led to the…

Computer Vision and Pattern Recognition · Computer Science 2024-07-11 An Zhang , Han Wang , Xiang Wang , Tat-Seng Chua

How to learn discriminative video representation from unlabeled videos is challenging but crucial for video analysis. The latest attempts seek to learn a representation model by predicting the appearance contents in the masked regions.…

Computer Vision and Pattern Recognition · Computer Science 2023-03-24 Xinyu Sun , Peihao Chen , Liangwei Chen , Changhao Li , Thomas H. Li , Mingkui Tan , Chuang Gan

We address the challenge of training Vision Transformers (ViTs) when labeled data is scarce but unlabeled data is abundant. We propose Semi-Supervised Masked Autoencoder (SSMAE), a framework that jointly optimizes masked image…

Computer Vision and Pattern Recognition · Computer Science 2026-01-29 Atik Faysal , Mohammad Rostami , Reihaneh Gh. Roshan , Nikhil Muralidhar , Huaxia Wang

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

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