{"url":"/method/dau-convnet","slug":"dau-convnet","name":"DAU-ConvNet","full_name":"Displaced Aggregation Units","full_name_withheld":false,"description_markdown":"**Displaced Aggregation Unit** replaces classic [convolution](https://paperswithcode.com/method/convolution) layer in ConvNets with learnable positions of units.  This introduces explicit structure of hierarchical compositions and results in several benefits:\r\n\r\n* fully adjustable and **learnable receptive fields** through spatially-adjustable filter units\r\n* **reduced parameters** for spatial coverage\r\nefficient inference\r\n* **decupling** of the parameters from the receptive field sizes\r\n\r\nMore information can be found [here.](https://www.vicos.si/Research/DeepCompositionalNet)","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/1902.07474v2","title":"Spatially-Adaptive Filter Units for Compact and Efficient Deep Neural Networks","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/skokec/DAU-ConvNet","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":2,"archive_num_papers":null,"papers_newest_first":[{"paper":"/paper/spatially-adaptive-filter-units-for-compact","title":"Spatially-Adaptive Filter Units for Compact and Efficient Deep Neural Networks","date":"2019-02-20","arxiv_id":"1902.07474","n_code_links":3,"syntology":null},{"paper":"/paper/spatially-adaptive-filter-units-for-deep","title":"Spatially-Adaptive Filter Units for Deep Neural Networks","date":"2017-11-30","arxiv_id":"1711.11473","n_code_links":2,"syntology":null}],"papers_shown":2,"tasks":[{"task":"/task/image-classification","name":"Image Classification","papers":2},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":2},{"task":"/task/blind-image-deblurring","name":"Blind Image Deblurring","papers":1},{"task":"/task/image-classification","name":"image-classification","papers":1}],"tasks_shown":4,"n_tasks":4,"usage_by_year":[{"year":"2017","papers":1},{"year":"2019","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/dau-convnet"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}