{"url":"/method/generalized-mean-pooling","slug":"generalized-mean-pooling","name":"Generalized Mean Pooling","full_name":"Generalized Mean Pooling","full_name_withheld":false,"description_markdown":"**Generalized Mean Pooling (GeM)** computes the generalized mean of each channel in a tensor. Formally:\r\n\r\n$$ \\textbf{e} = \\left[\\left(\\frac{1}{|\\Omega|}\\sum\\_{u\\in{\\Omega}}x^{p}\\_{cu}\\right)^{\\frac{1}{p}}\\right]\\_{c=1,\\cdots,C} $$\r\n\r\nwhere $p > 0$ is a parameter. Setting this exponent as $p > 1$ increases the contrast of the pooled feature map and focuses on the salient features of the image. GeM is a generalization of the [average pooling](https://paperswithcode.com/method/average-pooling) commonly used in classification networks ($p = 1$) and of spatial max-pooling layer ($p = \\infty$).\r\n\r\nSource: [MultiGrain](https://paperswithcode.com/method/multigrain)\r\n\r\nImage Source: [Eva Mohedano](https://www.google.com/url?sa=i&url=https%3A%2F%2Fwww.slideshare.net%2Fxavigiro%2Fd1l5-contentbased-image-retrieval-upc-2018-deep-learning-for-computer-vision&psig=AOvVaw2-9Hx23FNGFDe4GHU22Oo5&ust=1591798200590000&source=images&cd=vfe&ved=0CA0QjhxqFwoTCOiP-9P09OkCFQAAAAAdAAAAABAD)","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":"Pooling Operations","url":"/methods/category/pooling-operations","pwc_aliases":["pooling-operation"]}],"n_papers_tagged":6,"archive_num_papers":6,"papers_newest_first":[{"paper":"/paper/efficient-probabilistic-modeling-of","title":"Efficient Probabilistic Modeling of Crystallization at Mesoscopic Scale","date":"2024-05-26","arxiv_id":"2405.16608","n_code_links":1,"syntology":{"ran":10,"of":17,"unverified":7,"pointer_only":0}},{"paper":"/paper/minkunext-point-cloud-based-large-scale-place","title":"MinkUNeXt: Point Cloud-based Large-scale Place Recognition using 3D Sparse Convolutions","date":"2024-03-12","arxiv_id":"2403.07593","n_code_links":1,"syntology":null},{"paper":"/paper/gaitfm-fine-grained-motion-representation-for","title":"GaitMM: Multi-Granularity Motion Sequence Learning for Gait Recognition","date":"2022-09-18","arxiv_id":"2209.08470","n_code_links":1,"syntology":null},{"paper":null,"title":"Deep Learning Based Image Retrieval in the JPEG Compressed Domain","date":"2021-07-08","arxiv_id":"2107.03648","n_code_links":0,"syntology":null},{"paper":"/paper/unifying-deep-local-and-global-features-for","title":"Unifying Deep Local and Global Features for Image Search","date":"2020-01-14","arxiv_id":"2001.05027","n_code_links":5,"syntology":null},{"paper":"/paper/multigrain-a-unified-image-embedding-for","title":"MultiGrain: a unified image embedding for classes and instances","date":"2019-02-14","arxiv_id":"1902.05509","n_code_links":3,"syntology":{"ran":1,"of":4,"unverified":3,"pointer_only":0}}],"papers_shown":6,"tasks":[{"task":"/task/image-retrieval","name":"Image Retrieval","papers":3},{"task":"/task/retrieval","name":"Retrieval","papers":3},{"task":"/task/classification-1","name":"Classification","papers":1},{"task":"/task/content-based-image-retrieval","name":"Content-Based Image Retrieval","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/dimensionality-reduction","name":"Dimensionality Reduction","papers":1},{"task":"/task/gait-recognition","name":"Gait Recognition","papers":1},{"task":"/task/classification","name":"General Classification","papers":1},{"task":"/task/image-classification","name":"Image Classification","papers":1},{"task":"/task/multiview-gait-recognition","name":"Multiview Gait Recognition","papers":1},{"task":"/task/object","name":"Object","papers":1},{"task":"/task/philosophy","name":"Philosophy","papers":1},{"task":"/task/physical-simulations","name":"Physical Simulations","papers":1},{"task":"/task/image-classification","name":"image-classification","papers":1}],"tasks_shown":16,"n_tasks":16,"usage_by_year":[{"year":"2019","papers":1},{"year":"2020","papers":1},{"year":"2021","papers":1},{"year":"2022","papers":1},{"year":"2024","papers":2}],"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/generalized-mean-pooling"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}