Denoising Autoencoder
Description
A Denoising Autoencoder is a modification on the autoencoder to prevent the network learning the identity function. Specifically, if the autoencoder is too big, then it can just learn the data, so the output equals the input, and does not perform any useful representation learning or dimensionality reduction. Denoising autoencoders solve this problem by corrupting the input data on purpose, adding noise or masking some of the input values.
Image Credit: Kumar et al
Papers Using This Method
NAADA: A Noise-Aware Attention Denoising Autoencoder for Dental Panoramic Radiographs2025-06-24CWGAN-GP Augmented CAE for Jamming Detection in 5G-NR in Non-IID Datasets2025-06-18Demonstrating Superresolution in Radar Range Estimation Using a Denoising Autoencoder2025-06-17Impact of Bottleneck Layers and Skip Connections on the Generalization of Linear Denoising Autoencoders2025-05-30Automated Learning of Semantic Embedding Representations for Diffusion Models2025-05-09Snapshot Compressed Imaging Based Single-Measurement Computer Vision for Videos2025-01-25Targeted Adversarial Denoising Autoencoders (TADA) for Neural Time Series Filtration2025-01-09Developing Cryptocurrency Trading Strategy Based on Autoencoder-CNN-GANs Algorithms2024-12-24Machine Learning-Based Automated Assessment of Intracorporeal Suturing in Laparoscopic Fundoplication2024-12-16Detecting Visual Triggers in Cannabis Imagery: A CLIP-Based Multi-Labeling Framework with Local-Global Aggregation2024-11-22mDAE : modified Denoising AutoEncoder for missing data imputation2024-11-19Explainable Deep Learning Framework for SERS Bio-quantification2024-11-12Multi-head Sequence Tagging Model for Grammatical Error Correction2024-10-21TabSeq: A Framework for Deep Learning on Tabular Data via Sequential Ordering2024-10-17Conditional Lagrangian Wasserstein Flow for Time Series Imputation2024-10-10Aircraft Radar Altimeter Interference Mitigation Through a CNN-Layer Only Denoising Autoencoder Architecture2024-10-04TrustEMG-Net: Using Representation-Masking Transformer with U-Net for Surface Electromyography Enhancement2024-10-04Diffusion Models Learn Low-Dimensional Distributions via Subspace Clustering2024-09-04Learning to Enhance Aperture Phasor Field for Non-Line-of-Sight Imaging2024-07-26Improved Out-of-Scope Intent Classification with Dual Encoding and Threshold-based Re-Classification2024-05-30