{"url":"/method/octave-convolution","slug":"octave-convolution","name":"Octave Convolution","full_name":"Octave Convolution","full_name_withheld":false,"description_markdown":"An **Octave Convolution (OctConv)** stores and process feature maps that vary spatially “slower” at a lower spatial resolution reducing both memory and computation cost. It takes in feature maps containing tensors of two frequencies one octave apart, and extracts information directly from the\r\nlow-frequency maps without the need of decoding it back to the high-frequency. The motivation is that in natural images, information is conveyed at different frequencies where higher frequencies are usually encoded with fine details and lower frequencies are usually encoded with global structures.","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":"https://arxiv.org/abs/1904.05049v3","title":"Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/lxtGH/OctaveConv_pytorch/blob/079f7da29d55c2eeed8985d33f0b2f765d7a469e/libs/nn/OctaveConv2.py#L11","code_snippet_url_on_a_code_host":true,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Convolutions","url":"/methods/category/convolutions","pwc_aliases":[]}],"n_papers_tagged":9,"archive_num_papers":null,"papers_newest_first":[{"paper":"/paper/frequency-perception-network-for-camouflaged","title":"Frequency Perception Network for Camouflaged Object Detection","date":"2023-08-17","arxiv_id":"2308.08924","n_code_links":2,"syntology":null},{"paper":null,"title":"DCS-RISR: Dynamic Channel Splitting for Efficient Real-world Image Super-Resolution","date":"2022-12-15","arxiv_id":"2212.07613","n_code_links":0,"syntology":null},{"paper":"/paper/glioblastoma-multiforme-prognosis-mri-missing","title":"Glioblastoma Multiforme Prognosis: MRI Missing Modality Generation, Segmentation and Radiogenomic Survival Prediction","date":"2021-03-17","arxiv_id":"2104.01149","n_code_links":1,"syntology":null},{"paper":null,"title":"Mining Generalized Features for Detecting AI-Manipulated Fake Faces","date":"2020-10-27","arxiv_id":"2010.14129","n_code_links":0,"syntology":null},{"paper":"/paper/generalized-octave-convolutions-for-learned","title":"Generalized Octave Convolutions for Learned Multi-Frequency Image Compression","date":"2020-02-24","arxiv_id":"2002.10032","n_code_links":1,"syntology":null},{"paper":null,"title":"Classification of LiDAR Data Combined Octave Convolution With Capsule Network","date":"2020-01-09","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"title":"Multi-scale Octave Convolutions for Robust Speech Recognition","date":"2019-10-31","arxiv_id":"1910.14443","n_code_links":0,"syntology":null},{"paper":"/paper/accurate-retinal-vessel-segmentation-via","title":"Accurate Retinal Vessel Segmentation via Octave Convolution Neural Network","date":"2019-06-28","arxiv_id":"1906.12193","n_code_links":2,"syntology":null},{"paper":"/paper/drop-an-octave-reducing-spatial-redundancy-in","title":"Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution","date":"2019-04-10","arxiv_id":"1904.05049","n_code_links":28,"syntology":{"ran":14,"of":34,"unverified":20,"pointer_only":8}}],"papers_shown":9,"tasks":[{"task":"/task/decoder","name":"Decoder","papers":2},{"task":"/task/ssim","name":"SSIM","papers":2},{"task":"/task/segmentation","name":"Segmentation","papers":2},{"task":"/task/action-classification","name":"Action Classification","papers":1},{"task":"/task/classification-1","name":"Classification","papers":1},{"task":"/task/computational-efficiency","name":"Computational Efficiency","papers":1},{"task":"/task/denoising","name":"Denoising","papers":1},{"task":"/task/classification","name":"General Classification","papers":1},{"task":null,"name":"Generative Adversarial Network","papers":1},{"task":"/task/image-classification","name":"Image Classification","papers":1},{"task":"/task/image-compression","name":"Image Compression","papers":1},{"task":"/task/image-denoising","name":"Image Denoising","papers":1},{"task":"/task/image-super-resolution","name":"Image Super-Resolution","papers":1},{"task":"/task/ms-ssim","name":"MS-SSIM","papers":1},{"task":"/task/object","name":"Object","papers":1},{"task":"/task/object-detection","name":"Object Detection","papers":1},{"task":"/task/prediction","name":"Prediction","papers":1},{"task":"/task/prognosis","name":"Prognosis","papers":1},{"task":"/task/retinal-vessel-segmentation","name":"Retinal Vessel Segmentation","papers":1},{"task":"/task/robust-speech-recognition","name":"Robust Speech Recognition","papers":1}],"tasks_shown":20,"n_tasks":29,"usage_by_year":[{"year":"2019","papers":3},{"year":"2020","papers":3},{"year":"2021","papers":1},{"year":"2022","papers":1},{"year":"2023","papers":1}],"row_source":"embedded","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/octave-convolution"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}