{"url":"/method/temporal-dropout","slug":"temporal-dropout","name":"Temporal Dropout","full_name":"Temporal Dropout or TempD","full_name_withheld":false,"description_markdown":"A method that randomly mask out all features coming from a specific time-step in time-series data. If the model used is independent of uneven sequences or missing data in time-series, like attention-based transformers, the masked time-steps can be just ignored in the forward prediction of the model. Otherwise, they have to be masked out with some numerical value.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Crop Classification under Varying Cloud Cover with Neural Ordinary Differential Equations","paper":"/paper/crop-classification-under-varying-cloud-cover","first_author":"Nando Metzger","n_authors":5,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/crop-classification-under-varying-cloud-cover"},"source":{"url":"https://arxiv.org/abs/2012.02542v2","title":"Crop Classification under Varying Cloud Cover with Neural Ordinary Differential Equations","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"General","area_id":"general","collection":"Regularization","url":"/methods/category/regularization","pwc_aliases":[]}],"n_papers_tagged":5,"archive_num_papers":5,"papers_newest_first":[{"paper":"/paper/increasing-the-robustness-of-model","title":"Increasing the Robustness of Model Predictions to Missing Sensors in Earth Observation","date":"2024-07-22","arxiv_id":"2407.15512","n_code_links":2,"syntology":null},{"paper":"/paper/lightweight-pre-trained-transformers-for","title":"Lightweight, Pre-trained Transformers for Remote Sensing Timeseries","date":"2023-04-27","arxiv_id":"2304.14065","n_code_links":1,"syntology":{"ran":0,"of":13,"unverified":13,"pointer_only":0}},{"paper":"/paper/multi-modal-temporal-attention-models-for","title":"Multi-Modal Temporal Attention Models for Crop Mapping from Satellite Time Series","date":"2021-12-14","arxiv_id":"2112.07558","n_code_links":1,"syntology":null},{"paper":"/paper/fine-tuning-handwriting-recognition-systems","title":"Fine-tuning Handwriting Recognition systems with Temporal Dropout","date":"2021-01-31","arxiv_id":"2102.00511","n_code_links":1,"syntology":null},{"paper":"/paper/crop-classification-under-varying-cloud-cover","title":"Crop Classification under Varying Cloud Cover with Neural Ordinary Differential Equations","date":"2020-12-04","arxiv_id":"2012.02542","n_code_links":1,"syntology":null}],"papers_shown":5,"tasks":[{"task":"/task/crop-classification","name":"Crop Classification","papers":3},{"task":"/task/earth-observation","name":"Earth Observation","papers":2},{"task":"/task/time-series","name":"Time Series Analysis","papers":2},{"task":"/task/air-quality-inference","name":"Air Quality Inference","papers":1},{"task":"/task/classification","name":"General Classification","papers":1},{"task":"/task/handwriting-recognition","name":"Handwriting Recognition","papers":1},{"task":"/task/multi-view-learning","name":"MULTI-VIEW LEARNING","papers":1},{"task":"/task/panoptic-segmentation","name":"Panoptic Segmentation","papers":1},{"task":"/task/self-supervised-learning","name":"Self-Supervised Learning","papers":1},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":1},{"task":"/task/time-series-1","name":"Time Series","papers":1},{"task":"/task/transfer-learning","name":"Transfer Learning","papers":1}],"tasks_shown":12,"n_tasks":12,"usage_by_year":[{"year":"2020","papers":1},{"year":"2021","papers":2},{"year":"2023","papers":1},{"year":"2024","papers":1}],"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/temporal-dropout"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}