{"url":"/method/spatially-separable-convolution","slug":"spatially-separable-convolution","name":"Spatially Separable Convolution","full_name":"Spatially Separable Convolution","full_name_withheld":false,"description_markdown":"A **Spatially Separable Convolution** decomposes a [convolution](https://paperswithcode.com/method/convolution) into two separate operations. In regular convolution, if we have a 3 x 3 kernel then we directly convolve this with the image. We can divide a 3 x 3 kernel into a 3 x 1 kernel and a 1 x 3 kernel. Then, in spatially separable convolution, we first convolve the 3 x 1 kernel then the 1 x 3 kernel. This requires 6 instead of 9 parameters compared to regular convolution, and so it is more parameter efficient (additionally less matrix multiplications are required).\r\n\r\nImage Source: [Kunlun Bai](https://towardsdatascience.com/a-comprehensive-introduction-to-different-types-of-convolutions-in-deep-learning-669281e58215)","description_state":"present","introduced_year":null,"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":"Convolutions","url":"/methods/category/convolutions","pwc_aliases":[]}],"n_papers_tagged":12,"archive_num_papers":12,"papers_newest_first":[{"paper":null,"title":"SepHRNet: Generating High-Resolution Crop Maps from Remote Sensing imagery using HRNet with Separable Convolution","date":"2023-07-11","arxiv_id":"2307.05700","n_code_links":0,"syntology":null},{"paper":"/paper/eeea-net-an-early-exit-evolutionary-neural","title":"EEEA-Net: An Early Exit Evolutionary Neural Architecture Search","date":"2021-08-13","arxiv_id":"2108.06156","n_code_links":1,"syntology":null},{"paper":"/paper/neural-audio-fingerprint-for-high-specific","title":"Neural Audio Fingerprint for High-specific Audio Retrieval based on Contrastive Learning","date":"2020-10-22","arxiv_id":"2010.11910","n_code_links":3,"syntology":{"ran":1,"of":1,"unverified":0,"pointer_only":0}},{"paper":"/paper/relativenas-relative-neural-architecture","title":"RelativeNAS: Relative Neural Architecture Search via Slow-Fast Learning","date":"2020-09-14","arxiv_id":"2009.06193","n_code_links":2,"syntology":null},{"paper":null,"title":"GDP: Generalized Device Placement for Dataflow Graphs","date":"2019-09-28","arxiv_id":"1910.01578","n_code_links":0,"syntology":null},{"paper":"/paper/learning-data-augmentation-strategies-for","title":"Learning Data Augmentation Strategies for Object Detection","date":"2019-06-26","arxiv_id":"1906.11172","n_code_links":6,"syntology":{"ran":3,"of":3,"unverified":0,"pointer_only":3}},{"paper":"/paper/190503696","title":"HAWQ: Hessian AWare Quantization of Neural Networks with Mixed-Precision","date":"2019-04-29","arxiv_id":"1905.03696","n_code_links":1,"syntology":{"ran":1,"of":3,"unverified":2,"pointer_only":3}},{"paper":"/paper/nas-fpn-learning-scalable-feature-pyramid","title":"NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection","date":"2019-04-16","arxiv_id":"1904.07392","n_code_links":8,"syntology":null},{"paper":"/paper/anode-unconditionally-accurate-memory","title":"ANODE: Unconditionally Accurate Memory-Efficient Gradients for Neural ODEs","date":"2019-02-27","arxiv_id":"1902.10298","n_code_links":5,"syntology":{"ran":2,"of":7,"unverified":5,"pointer_only":1}},{"paper":"/paper/gpipe-efficient-training-of-giant-neural","title":"GPipe: Efficient Training of Giant Neural Networks using Pipeline Parallelism","date":"2018-11-16","arxiv_id":"1811.06965","n_code_links":13,"syntology":{"ran":1,"of":25,"unverified":24,"pointer_only":16}},{"paper":"/paper/squeezenext-hardware-aware-neural-network","title":"SqueezeNext: Hardware-Aware Neural Network Design","date":"2018-03-23","arxiv_id":"1803.10615","n_code_links":8,"syntology":{"ran":1,"of":1,"unverified":0,"pointer_only":0}},{"paper":"/paper/regularized-evolution-for-image-classifier","title":"Regularized Evolution for Image Classifier Architecture Search","date":"2018-02-05","arxiv_id":"1802.01548","n_code_links":5,"syntology":null}],"papers_shown":12,"tasks":[{"task":"/task/image-classification","name":"Image Classification","papers":4},{"task":"/task/architecture-search","name":"Neural Architecture Search","papers":4},{"task":"/task/object-detection","name":"Object Detection","papers":4},{"task":"/task/object-detection-1","name":"object-detection","papers":4},{"task":null,"name":"GPU","papers":2},{"task":"/task/keypoint-detection","name":"Keypoint Detection","papers":2},{"task":"/task/object","name":"Object","papers":2},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":2},{"task":"/task/image-classification","name":"image-classification","papers":2},{"task":"/task/audio-fingerprint","name":"Audio Fingerprint","papers":1},{"task":"/task/clustering-multivariate-time-series","name":"Clustering Multivariate Time Series","papers":1},{"task":"/task/contrastive-learning","name":"Contrastive Learning","papers":1},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":1},{"task":"/task/decoder","name":"Decoder","papers":1},{"task":"/task/deep-learning","name":"Deep Learning","papers":1},{"task":"/task/earth-observation","name":"Earth Observation","papers":1},{"task":"/task/evolutionary-algorithms","name":"Evolutionary Algorithms","papers":1},{"task":"/task/fine-grained-image-classification","name":"Fine-Grained Image Classification","papers":1},{"task":"/task/graph-neural-network","name":"Graph Neural Network","papers":1},{"task":"/task/image-augmentation","name":"Image Augmentation","papers":1}],"tasks_shown":20,"n_tasks":29,"usage_by_year":[{"year":"2018","papers":3},{"year":"2019","papers":5},{"year":"2020","papers":2},{"year":"2021","papers":1},{"year":"2023","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/spatially-separable-convolution"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}