{"url":"/method/context-enhancement-module","slug":"context-enhancement-module","name":"Context Enhancement Module","full_name":"Context Enhancement Module","full_name_withheld":false,"description_markdown":"**Context Enhancement Module (CEM)** is a feature extraction module used in object detection (specifically, [ThunderNet](https://paperswithcode.com/method/thundernet)) which aims to  to enlarge the receptive field. The key idea of CEM is to aggregate multi-scale local context information and global context information to generate more discriminative features. In CEM, the feature maps from three scales are merged: $C\\_{4}$, $C\\_{5}$ and $C\\_{glb}$. $C\\_{glb}$ is the global context feature vector by applying a [global average pooling](https://paperswithcode.com/method/global-average-pooling) on $C\\_{5}$. We then apply a 1 × 1 [convolution](https://paperswithcode.com/method/convolution) on each feature map to squeeze the number of channels to $\\alpha \\times p \\times p = 245$.\r\n\r\nAfterwards, $C\\_{5}$ is upsampled by 2× and $C\\_{glb}$ is broadcast so that the spatial dimensions of the three feature maps are\r\nequal. At last, the three generated feature maps are aggregated. By leveraging both local and global context, CEM effectively enlarges the receptive field and refines the representation ability of the thin feature map. Compared with prior [FPN](https://paperswithcode.com/method/fpn) structures, CEM involves only two 1×1 convolutions and a fc layer.","description_state":"present","introduced_year":null,"introduced_by":{"title":"ThunderNet: Towards Real-time Generic Object Detection","paper":"/paper/thundernet-towards-real-time-generic-object","first_author":"Zheng Qin","n_authors":7,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/thundernet-towards-real-time-generic-object"},"source":{"url":"https://arxiv.org/abs/1903.11752v3","title":"ThunderNet: Towards Real-time Generic Object Detection","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/ouyanghuiyu/Thundernet_Pytorch/blob/ab66b733a39c9d1c60b5373f84f861d9627d8c20/lib/model/faster_rcnn/modules.py#L21","code_snippet_url_on_a_code_host":true,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Feature Extractors","url":"/methods/category/feature-extractors","pwc_aliases":[]}],"n_papers_tagged":8,"archive_num_papers":8,"papers_newest_first":[{"paper":null,"title":"Hybrid Local-Global Context Learning for Neural Video Compression","date":"2024-11-30","arxiv_id":"2412.00446","n_code_links":0,"syntology":null},{"paper":"/paper/a-late-stage-bitemporal-feature-fusion","title":"A Late-Stage Bitemporal Feature Fusion Network for Semantic Change Detection","date":"2024-06-15","arxiv_id":"2406.10678","n_code_links":1,"syntology":null},{"paper":null,"title":"Real Time Egocentric Segmentation for Video-self Avatar in Mixed Reality","date":"2022-07-04","arxiv_id":"2207.01296","n_code_links":0,"syntology":null},{"paper":"/paper/ce-fpn-enhancing-channel-information-for","title":"CE-FPN: Enhancing Channel Information for Object Detection","date":"2021-03-19","arxiv_id":"2103.10643","n_code_links":1,"syntology":null},{"paper":null,"title":"Egocentric Human Segmentation for Mixed Reality","date":"2020-05-25","arxiv_id":"2005.12074","n_code_links":0,"syntology":null},{"paper":null,"title":"ThunderNet: Towards Real-Time Generic Object Detection on Mobile Devices","date":"2019-10-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"title":"AFP-Net: Realtime Anchor-Free Polyp Detection in Colonoscopy","date":"2019-09-05","arxiv_id":"1909.02477","n_code_links":0,"syntology":null},{"paper":"/paper/thundernet-towards-real-time-generic-object","title":"ThunderNet: Towards Real-time Generic Object Detection","date":"2019-03-28","arxiv_id":"1903.11752","n_code_links":3,"syntology":null}],"papers_shown":8,"tasks":[{"task":"/task/object-detection","name":"Object Detection","papers":4},{"task":"/task/object-detection-1","name":"object-detection","papers":4},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":3},{"task":"/task/mixed-reality","name":"Mixed Reality","papers":2},{"task":"/task/object","name":"Object","papers":2},{"task":"/task/segmentation","name":"Segmentation","papers":2},{"task":"/task/change-detection","name":"Change Detection","papers":1},{"task":"/task/earth-observation","name":"Earth Observation","papers":1},{"task":"/task/miscellaneous","name":"Miscellaneous","papers":1},{"task":"/task/motion-compensation","name":"Motion Compensation","papers":1},{"task":"/task/motion-estimation","name":"Motion Estimation","papers":1},{"task":"/task/multi-task-learning","name":"Multi-Task Learning","papers":1},{"task":"/task/optical-flow-estimation","name":"Optical Flow Estimation","papers":1},{"task":"/task/video-compression","name":"Video Compression","papers":1}],"tasks_shown":14,"n_tasks":14,"usage_by_year":[{"year":"2019","papers":3},{"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/context-enhancement-module"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}