Related papers: A$^{2}$-MAE: A spatial-temporal-spectral unified r…
Self-supervised learning has been a powerful training paradigm to facilitate representation learning. In this study, we design a masked autoencoder (MAE) to guide deep learning models to learn electroencephalography (EEG) signal…
Recently, various studies have been directed towards exploring dense passage retrieval techniques employing pre-trained language models, among which the masked auto-encoder (MAE) pre-training architecture has emerged as the most promising.…
Learning aligned multimodal embeddings from weakly paired, label-free corpora is challenging: pipelines often provide only pre-extracted features, clips contain multiple events, and spurious co-occurrences. We propose HSC-MAE (Hierarchical…
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…
End-to-end Speech-to-text Translation (E2E-ST), which directly translates source language speech to target language text, is widely useful in practice, but traditional cascaded approaches (ASR+MT) often suffer from error propagation in the…
The ubiquity of missing data in urban intelligence systems, attributable to adverse environmental conditions and equipment failures, poses a significant challenge to the efficacy of downstream applications, notably in the realms of traffic…
Large-scale self-supervised pre-training Transformer architecture have significantly boosted the performance for various tasks in natural language processing (NLP) and computer vision (CV). However, there is a lack of researches on…
This work proposes a unified self-supervised pre-training framework for transferable multi-modal perception representation learning via masked multi-modal reconstruction in Neural Radiance Field (NeRF), namely NeRF-Supervised Masked…
Achieving agile and generalized legged locomotion across terrains requires tight integration of perception and control, especially under occlusions and sparse footholds. Existing methods have demonstrated agility on parkour courses but…
Masked point modeling methods have recently achieved great success in self-supervised learning for point cloud data. However, these methods are sensitive to rotations and often exhibit sharp performance drops when encountering rotational…
Unsupervised visual anomaly detection conveys practical significance in many scenarios and is a challenging task due to the unbounded definition of anomalies. Moreover, most previous methods are application-specific, and establishing a…
The multi-modal remote sensing foundation model (MM-RSFM) has significantly advanced various Earth observation tasks, such as urban planning, environmental monitoring, and natural disaster management. However, most existing approaches…
Steered-Mixtures-of-Experts (SMoE) models provide sparse, edge-aware representations, applicable to many use-cases in image processing. This includes denoising, super-resolution and compression of 2D- and higher dimensional pixel data.…
Polysomnography (PSG) signals are essential for studying sleep processes and diagnosing sleep disorders. Analyzing PSG data through deep neural networks (DNNs) for automated sleep monitoring has become increasingly feasible. However, the…
The computer vision domain has greatly benefited from an abundance of data across many modalities to improve on various visual tasks. Recently, there has been a lot of focus on self-supervised pre-training methods through Masked…
Existing rotation-invariant point cloud masked autoencoders (MAE) rely on random masking strategies that overlook geometric structure and semantic coherence. Random masking treats patches independently, failing to capture spatial…
Unsupervised learning methods have become increasingly important in deep learning due to their demonstrated large utilization of datasets and higher accuracy in computer vision and natural language processing tasks. There is a growing trend…
From optical sensors to microwave radars, leveraging the complementary strengths of remote sensing (RS) sensors is crucial for achieving dense spatio-temporal monitoring of our planet. In contrast, recent deep learning models, whether…
We present a novel masked image modeling (MIM) approach, context autoencoder (CAE), for self-supervised representation pretraining. We pretrain an encoder by making predictions in the encoded representation space. The pretraining tasks…
Self-supervised learning (SSL) enables learning useful inductive biases through utilizing pretext tasks that require no labels. The unlabeled nature of SSL makes it especially important for whole slide histopathological images (WSIs), where…