{"url":"/method/droppath","slug":"droppath","name":"DropPath","full_name":"DropPath","full_name_withheld":false,"description_markdown":"Just as [dropout](https://paperswithcode.com/method/dropout) prevents co-adaptation of activations, **DropPath** prevents co-adaptation of parallel paths in networks such as [FractalNets](https://paperswithcode.com/method/fractalnet) by randomly dropping operands of the join layers. This\r\ndiscourages the network from using one input path as an anchor and another as a corrective term (a\r\nconfiguration that, if not prevented, is prone to overfitting). Two sampling strategies are:\r\n\r\n- **Local**: a join drops each input with fixed probability, but we make sure at least one survives.\r\n- **Global**: a single path is selected for the entire network. We restrict this path to be a single\r\ncolumn, thereby promoting individual columns as independently strong predictors.","description_state":"present","introduced_year":null,"introduced_by":{"title":"FractalNet: Ultra-Deep Neural Networks without Residuals","paper":"/paper/fractalnet-ultra-deep-neural-networks-without","first_author":"Gustav Larsson","n_authors":3,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/fractalnet-ultra-deep-neural-networks-without"},"source":{"url":"http://arxiv.org/abs/1605.07648v4","title":"FractalNet: Ultra-Deep Neural Networks without Residuals","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/osmr/imgclsmob/blob/aa6c6186d2e296bf0687f2c0ab6454f33f5ef4f3/pytorch/pytorchcv/models/fractalnet_cifar.py#L146","code_snippet_url_on_a_code_host":true,"categories":[{"area":"General","area_id":"general","collection":"Regularization","url":"/methods/category/regularization","pwc_aliases":[]}],"n_papers_tagged":22,"archive_num_papers":22,"papers_newest_first":[{"paper":null,"title":"Masked Transformer for Electrocardiogram Classification","date":"2023-08-31","arxiv_id":"2309.07136","n_code_links":0,"syntology":null},{"paper":"/paper/lightweight-neural-architecture-search-for","title":"Lightweight Neural Architecture Search for Temporal Convolutional Networks at the Edge","date":"2023-01-24","arxiv_id":"2301.10281","n_code_links":1,"syntology":null},{"paper":"/paper/mobyv2al-self-supervised-active-learning-for","title":"MoBYv2AL: Self-supervised Active Learning for Image Classification","date":"2023-01-04","arxiv_id":"2301.01531","n_code_links":1,"syntology":null},{"paper":"/paper/nas-lid-efficient-neural-architecture-search","title":"NAS-LID: Efficient Neural Architecture Search with Local Intrinsic Dimension","date":"2022-11-23","arxiv_id":"2211.12759","n_code_links":1,"syntology":null},{"paper":"/paper/delving-into-masked-autoencoders-for-multi","title":"Delving into Masked Autoencoders for Multi-Label Thorax Disease Classification","date":"2022-10-23","arxiv_id":"2210.12843","n_code_links":1,"syntology":{"ran":0,"of":2,"unverified":2,"pointer_only":0}},{"paper":"/paper/agnas-attention-guided-micro-and-macro","title":"AGNAS: Attention-Guided Micro- and Macro-Architecture Search","date":"2022-06-05","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"title":"Search Space Adaptation for Differentiable Neural Architecture Search in Image Classification","date":"2022-06-05","arxiv_id":"2206.02098","n_code_links":0,"syntology":null},{"paper":"/paper/generalizing-few-shot-nas-with-gradient-1","title":"Generalizing Few-Shot NAS with Gradient Matching","date":"2022-03-29","arxiv_id":"2203.15207","n_code_links":1,"syntology":{"ran":0,"of":7,"unverified":7,"pointer_only":0}},{"paper":null,"title":"Towards Tailored Models on Private AIoT Devices: Federated Direct Neural Architecture Search","date":"2022-02-23","arxiv_id":"2202.11490","n_code_links":0,"syntology":null},{"paper":null,"title":"Data-Free Neural Architecture Search via Recursive Label Calibration","date":"2021-12-03","arxiv_id":"2112.02086","n_code_links":0,"syntology":null},{"paper":"/paper/profiling-neural-blocks-and-design-spaces-for","title":"Profiling Neural Blocks and Design Spaces for Mobile Neural Architecture Search","date":"2021-09-25","arxiv_id":"2109.12426","n_code_links":1,"syntology":null},{"paper":null,"title":"Federated Model Search via Reinforcement Learning","date":"2021-07-07","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"title":"Generative Adversarial Neural Architecture Search","date":"2021-05-19","arxiv_id":"2105.09356","n_code_links":0,"syntology":null},{"paper":"/paper/self-supervised-learning-with-swin","title":"Self-Supervised Learning with Swin Transformers","date":"2021-05-10","arxiv_id":"2105.04553","n_code_links":6,"syntology":null},{"paper":"/paper/generalized-latency-performance-estimation","title":"Generalized Latency Performance Estimation for Once-For-All Neural Architecture Search","date":"2021-01-04","arxiv_id":"2101.00732","n_code_links":2,"syntology":null},{"paper":"/paper/efficient-neural-architecture-search-for-end","title":"Efficient Neural Architecture Search for End-to-end Speech Recognition via Straight-Through Gradients","date":"2020-11-11","arxiv_id":"2011.05649","n_code_links":1,"syntology":null},{"paper":null,"title":"How Does Supernet Help in Neural Architecture Search?","date":"2020-10-16","arxiv_id":"2010.08219","n_code_links":0,"syntology":null},{"paper":"/paper/angle-based-search-space-shrinking-for-neural","title":"Angle-based Search Space Shrinking for Neural Architecture Search","date":"2020-04-28","arxiv_id":"2004.13431","n_code_links":1,"syntology":{"ran":2,"of":4,"unverified":2,"pointer_only":0}},{"paper":"/paper/unas-differentiable-architecture-search-meets","title":"UNAS: Differentiable Architecture Search Meets Reinforcement Learning","date":"2019-12-16","arxiv_id":"1912.07651","n_code_links":1,"syntology":null},{"paper":"/paper/neural-predictor-for-neural-architecture","title":"Neural Predictor for Neural Architecture Search","date":"2019-12-02","arxiv_id":"1912.00848","n_code_links":2,"syntology":{"ran":0,"of":10,"unverified":10,"pointer_only":0}},{"paper":"/paper/proxylessnas-direct-neural-architecture","title":"ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware","date":"2018-12-02","arxiv_id":"1812.00332","n_code_links":23,"syntology":{"ran":5,"of":27,"unverified":22,"pointer_only":0}},{"paper":"/paper/fractalnet-ultra-deep-neural-networks-without","title":"FractalNet: Ultra-Deep Neural Networks without Residuals","date":"2016-05-24","arxiv_id":"1605.07648","n_code_links":4,"syntology":{"ran":4,"of":6,"unverified":2,"pointer_only":1}}],"papers_shown":22,"tasks":[{"task":"/task/architecture-search","name":"Neural Architecture Search","papers":16},{"task":"/task/image-classification","name":"Image Classification","papers":6},{"task":null,"name":"GPU","papers":4},{"task":"/task/image-classification","name":"image-classification","papers":3},{"task":"/task/classification-1","name":"Classification","papers":2},{"task":"/task/federated-learning","name":"Federated Learning","papers":2},{"task":"/task/object-detection","name":"Object Detection","papers":2},{"task":"/task/reinforcement-learning","name":"Reinforcement Learning","papers":2},{"task":"/task/reinforcement-learning-1","name":"Reinforcement Learning (RL)","papers":2},{"task":"/task/self-supervised-learning","name":"Self-Supervised Learning","papers":2},{"task":"/task/time-series-1","name":"Time Series","papers":2},{"task":"/task/object-detection-1","name":"object-detection","papers":2},{"task":"/task/reinforcement-learning-2","name":"reinforcement-learning","papers":2},{"task":"/task/active-learning","name":"Active Learning","papers":1},{"task":"/task/all","name":"All","papers":1},{"task":"/task/automatic-speech-recognition-2","name":"Automatic Speech Recognition","papers":1},{"task":"/task/automatic-speech-recognition","name":"Automatic Speech Recognition (ASR)","papers":1},{"task":"/task/computational-efficiency","name":"Computational Efficiency","papers":1},{"task":"/task/diagnostic","name":"Diagnostic","papers":1},{"task":"/task/diversity","name":"Diversity","papers":1}],"tasks_shown":20,"n_tasks":34,"usage_by_year":[{"year":"2016","papers":1},{"year":"2018","papers":1},{"year":"2019","papers":2},{"year":"2020","papers":3},{"year":"2021","papers":6},{"year":"2022","papers":6},{"year":"2023","papers":3}],"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/droppath"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}