相关论文: Masked Autoencoders that Listen

Featurizing microscopy images for use in biological research remains a significant challenge, especially for large-scale experiments spanning millions of images. This work explores the scaling properties of weakly supervised classifiers and…

Learning representations from videos requires understanding continuous motion and visual correspondences between frames. In this paper, we introduce the Concatenated Masked Autoencoders (CatMAE) as a spatial-temporal learner for…

Low-dose computed tomography (LDCT) offers reduced X-ray radiation exposure but at the cost of compromised image quality, characterized by increased noise and artifacts. Recently, transformer models emerged as a promising avenue to enhance…

Pre-training by numerous image data has become de-facto for robust 2D representations. In contrast, due to the expensive data acquisition and annotation, a paucity of large-scale 3D datasets severely hinders the learning for high-quality 3D…

Building robust medical machine learning systems requires pretraining strategies that exploit the intrinsic structure present in clinical data. We introduce Multiview Masked Autoencoder (MVMAE), a self-supervised framework that leverages…

The Variational Autoencoder (VAE) is a powerful deep generative model that is now extensively used to represent high-dimensional complex data via a low-dimensional latent space learned in an unsupervised manner. In the original VAE model,…

We introduce a self-supervised speech pre-training method called TERA, which stands for Transformer Encoder Representations from Alteration. Recent approaches often learn by using a single auxiliary task like contrastive prediction,…

In this paper, we present EH-MAM (Easy-to-Hard adaptive Masked Acoustic Modeling), a novel self-supervised learning approach for speech representation learning. In contrast to the prior methods that use random masking schemes for Masked…

For many Automatic Speech Recognition (ASR) tasks audio features as spectrograms show better results than Mel-frequency Cepstral Coefficients (MFCC), but in practice they are hard to use due to a complex dimensionality of a feature space.…

Autoencoders have emerged as powerful models for visualization and dimensionality reduction based on the fundamental assumption that high-dimensional data is generated from a low-dimensional manifold. A critical challenge in autoencoder…

We propose bootstrapped masked autoencoders (BootMAE), a new approach for vision BERT pretraining. BootMAE improves the original masked autoencoders (MAE) with two core designs: 1) momentum encoder that provides online feature as extra BERT…

In this paper, we propose Language-Guided Contrastive Audio-Visual Masked Autoencoders (LG-CAV-MAE) to improve audio-visual representation learning. LG-CAV-MAE integrates a pretrained text encoder into contrastive audio-visual masked…

Growing techniques have been emerging to improve the performance of passage retrieval. As an effective representation bottleneck pretraining technique, the contextual masked auto-encoder utilizes contextual embedding to assist in the…

Federated learning is a specific distributed learning paradigm in which a central server aggregates updates from multiple clients' local models, thereby enabling the server to learn without requiring clients to upload their private data,…

Remote sensing images present unique challenges to image analysis due to the extensive geographic coverage, hardware limitations, and misaligned multi-scale images. This paper revisits the classical multi-scale representation learning…

Decoding speech from non-invasive brain signals, such as electroencephalography (EEG), has the potential to advance brain-computer interfaces (BCIs), with applications in silent communication and assistive technologies for individuals with…

Self-supervised learning (SSL) has recently emerged as a key strategy for building foundation models in remote sensing, where the scarcity of annotated data limits the applicability of fully supervised approaches. In this work, we introduce…

Vision Transformers (ViTs) outperforms convolutional neural networks (CNNs) in several vision tasks with its global modeling capabilities. However, ViT lacks the inductive bias inherent to convolution making it require a large amount of…

Multivariate Time Series forecasting has been an increasingly popular topic in various applications and scenarios. Recently, contrastive learning and Transformer-based models have achieved good performance in many long-term series…

Most existing masked audio modeling (MAM) methods learn audio representations by masking and reconstructing local spectrogram patches. However, the reconstruction loss mainly accounts for the signal-level quality of the reconstructed…