{"url":"/method/denoising-autoencoder","slug":"denoising-autoencoder","name":"Denoising Autoencoder","full_name":"Denoising Autoencoder","full_name_withheld":false,"description_markdown":"A **Denoising Autoencoder** is a modification on the [autoencoder](https://paperswithcode.com/method/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.\r\n\r\nImage Credit: [Kumar et al](https://www.semanticscholar.org/paper/Static-hand-gesture-recognition-using-stacked-Kumar-Nandi/5191ddf3f0841c89ba9ee592a2f6c33e4a40d4bf)","description_state":"present","introduced_year":2008,"introduced_by":{"title":null,"paper":null,"first_author":null,"n_authors":0,"url_abs":null,"archive_paper_url":null},"source":{"url":null,"title":null,"url_on_a_paper_host":false},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Generative Models","url":"/methods/category/generative-models","pwc_aliases":[]}],"n_papers_tagged":182,"archive_num_papers":182,"papers_newest_first":[{"paper":null,"title":"NAADA: A Noise-Aware Attention Denoising Autoencoder for Dental Panoramic Radiographs","date":"2025-06-24","arxiv_id":"2506.19387","n_code_links":0,"syntology":null},{"paper":null,"title":"CWGAN-GP Augmented CAE for Jamming Detection in 5G-NR in Non-IID Datasets","date":"2025-06-18","arxiv_id":"2506.15075","n_code_links":0,"syntology":null},{"paper":null,"title":"Demonstrating Superresolution in Radar Range Estimation Using a Denoising Autoencoder","date":"2025-06-17","arxiv_id":"2506.14906","n_code_links":0,"syntology":null},{"paper":null,"title":"Impact of Bottleneck Layers and Skip Connections on the Generalization of Linear Denoising Autoencoders","date":"2025-05-30","arxiv_id":"2505.24668","n_code_links":0,"syntology":null},{"paper":null,"title":"Automated Learning of Semantic Embedding Representations for Diffusion Models","date":"2025-05-09","arxiv_id":"2505.05732","n_code_links":0,"syntology":null},{"paper":null,"title":"Snapshot Compressed Imaging Based Single-Measurement Computer Vision for Videos","date":"2025-01-25","arxiv_id":"2501.15122","n_code_links":0,"syntology":null},{"paper":null,"title":"Targeted Adversarial Denoising Autoencoders (TADA) for Neural Time Series Filtration","date":"2025-01-09","arxiv_id":"2501.04967","n_code_links":0,"syntology":null},{"paper":null,"title":"Developing Cryptocurrency Trading Strategy Based on Autoencoder-CNN-GANs Algorithms","date":"2024-12-24","arxiv_id":"2412.18202","n_code_links":0,"syntology":null},{"paper":null,"title":"Machine Learning-Based Automated Assessment of Intracorporeal Suturing in Laparoscopic Fundoplication","date":"2024-12-16","arxiv_id":"2412.16195","n_code_links":0,"syntology":null},{"paper":null,"title":"Detecting Visual Triggers in Cannabis Imagery: A CLIP-Based Multi-Labeling Framework with Local-Global Aggregation","date":"2024-11-22","arxiv_id":"2412.08648","n_code_links":0,"syntology":null},{"paper":null,"title":"mDAE : modified Denoising AutoEncoder for missing data imputation","date":"2024-11-19","arxiv_id":"2411.12847","n_code_links":0,"syntology":null},{"paper":null,"title":"Explainable Deep Learning Framework for SERS Bio-quantification","date":"2024-11-12","arxiv_id":"2411.08082","n_code_links":0,"syntology":null},{"paper":"/paper/multi-head-sequence-tagging-model-for","title":"Multi-head Sequence Tagging Model for Grammatical Error Correction","date":"2024-10-21","arxiv_id":"2410.16473","n_code_links":2,"syntology":null},{"paper":"/paper/tabseq-a-framework-for-deep-learning-on","title":"TabSeq: A Framework for Deep Learning on Tabular Data via Sequential Ordering","date":"2024-10-17","arxiv_id":"2410.13203","n_code_links":1,"syntology":null},{"paper":null,"title":"Conditional Lagrangian Wasserstein Flow for Time Series Imputation","date":"2024-10-10","arxiv_id":"2410.07550","n_code_links":0,"syntology":null},{"paper":null,"title":"Aircraft Radar Altimeter Interference Mitigation Through a CNN-Layer Only Denoising Autoencoder Architecture","date":"2024-10-04","arxiv_id":"2410.03423","n_code_links":0,"syntology":null},{"paper":"/paper/trustemg-net-using-representation-masking","title":"TrustEMG-Net: Using Representation-Masking Transformer with U-Net for Surface Electromyography Enhancement","date":"2024-10-04","arxiv_id":"2410.03843","n_code_links":1,"syntology":null},{"paper":"/paper/diffusion-models-learn-low-dimensional","title":"Diffusion Models Learn Low-Dimensional Distributions via Subspace Clustering","date":"2024-09-04","arxiv_id":"2409.02426","n_code_links":1,"syntology":{"ran":3,"of":4,"unverified":1,"pointer_only":4}},{"paper":"/paper/learning-to-enhance-aperture-phasor-field-for","title":"Learning to Enhance Aperture Phasor Field for Non-Line-of-Sight Imaging","date":"2024-07-26","arxiv_id":"2407.18574","n_code_links":1,"syntology":null},{"paper":"/paper/improved-out-of-scope-intent-classification","title":"Improved Out-of-Scope Intent Classification with Dual Encoding and Threshold-based Re-Classification","date":"2024-05-30","arxiv_id":"2405.19967","n_code_links":1,"syntology":null},{"paper":"/paper/combining-denoising-autoencoders-with","title":"Combining Denoising Autoencoders with Contrastive Learning to fine-tune Transformer Models","date":"2024-05-23","arxiv_id":"2405.14437","n_code_links":1,"syntology":null},{"paper":"/paper/multimae-der-multimodal-masked-autoencoder","title":"MultiMAE-DER: Multimodal Masked Autoencoder for Dynamic Emotion Recognition","date":"2024-04-28","arxiv_id":"2404.18327","n_code_links":1,"syntology":null},{"paper":null,"title":"DoughNet: A Visual Predictive Model for Topological Manipulation of Deformable Objects","date":"2024-04-18","arxiv_id":"2404.12524","n_code_links":0,"syntology":null},{"paper":"/paper/do-we-really-need-imputation-in-automl","title":"Do We Really Need Imputation in AutoML Predictive Modeling?","date":"2024-04-12","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"title":"Fréchet Denoised Distance: Enhancing Plausibility Evaluation for Generated Designs with Denoising Autoencoder","date":"2024-03-08","arxiv_id":"2403.05352","n_code_links":0,"syntology":null},{"paper":"/paper/deconstructing-denoising-diffusion-models-for","title":"Deconstructing Denoising Diffusion Models for Self-Supervised Learning","date":"2024-01-25","arxiv_id":"2401.14404","n_code_links":1,"syntology":{"ran":11,"of":15,"unverified":4,"pointer_only":15}},{"paper":null,"title":"Diffusion Model with Perceptual Loss","date":"2023-12-30","arxiv_id":"2401.00110","n_code_links":0,"syntology":null},{"paper":"/paper/malpurifier-enhancing-android-malware","title":"MalPurifier: Enhancing Android Malware Detection with Adversarial Purification against Evasion Attacks","date":"2023-12-11","arxiv_id":"2312.06423","n_code_links":1,"syntology":null},{"paper":"/paper/opening-the-black-box-towards-inherently","title":"Opening the Black Box: Towards inherently interpretable energy data imputation models using building physics insight","date":"2023-11-28","arxiv_id":"2311.16632","n_code_links":1,"syntology":null},{"paper":"/paper/eeg-connectivity-analysis-using-denoising","title":"EEG Connectivity Analysis Using Denoising Autoencoders for the Detection of Dyslexia","date":"2023-11-23","arxiv_id":"2311.13876","n_code_links":1,"syntology":null}],"papers_shown":30,"tasks":[{"task":"/task/denoising","name":"Denoising","papers":177},{"task":"/task/decoder","name":"Decoder","papers":14},{"task":"/task/deep-learning","name":"Deep Learning","papers":10},{"task":"/task/classification","name":"General Classification","papers":10},{"task":"/task/imputation","name":"Imputation","papers":9},{"task":"/task/representation-learning","name":"Representation Learning","papers":9},{"task":"/task/translation","name":"Translation","papers":9},{"task":"/task/anomaly-detection","name":"Anomaly Detection","papers":7},{"task":"/task/dimensionality-reduction","name":"Dimensionality Reduction","papers":7},{"task":"/task/time-series-1","name":"Time Series","papers":7},{"task":"/task/classification-1","name":"Classification","papers":6},{"task":"/task/clustering","name":"Clustering","papers":6},{"task":"/task/domain-adaptation","name":"Domain Adaptation","papers":6},{"task":"/task/language-modelling","name":"Language Modelling","papers":6},{"task":"/task/time-series","name":"Time Series Analysis","papers":6},{"task":"/task/dictionary-learning","name":"Dictionary Learning","papers":5},{"task":"/task/language-modeling","name":"Language Modeling","papers":5},{"task":"/task/machine-translation","name":"Machine Translation","papers":5},{"task":"/task/self-supervised-learning","name":"Self-Supervised Learning","papers":5},{"task":"/task/transfer-learning","name":"Transfer Learning","papers":5}],"tasks_shown":20,"n_tasks":199,"usage_by_year":[{"year":"2013","papers":2},{"year":"2014","papers":4},{"year":"2015","papers":11},{"year":"2016","papers":6},{"year":"2017","papers":8},{"year":"2018","papers":13},{"year":"2019","papers":25},{"year":"2020","papers":28},{"year":"2021","papers":21},{"year":"2022","papers":19},{"year":"2023","papers":19},{"year":"2024","papers":19},{"year":"2025","papers":7}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/denoising-autoencoder"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}