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