Methods › Computer Vision › Feature Extractors › Context Enhancement Module
Context Enhancement Module
Introduced by Zheng Qin et al. in ThunderNet: Towards Real-time Generic Object Detection
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Context Enhancement Module (CEM) is a feature extraction module used in object detection (specifically, 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: C₄, C₅ and C_(glb). C_(glb) is the global context feature vector by applying a global average pooling on C₅. We then apply a 1 × 1 convolution on each feature map to squeeze the number of channels to α×p ×p = 245.
Afterwards, C₅ is upsampled by 2× and C_(glb) is broadcast so that the spatial dimensions of the three feature maps are equal. 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 structures, CEM involves only two 1×1 convolutions and a fc layer.
Papers archive 2025-07-28
8 shown of 8, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
Hybrid Local-Global Context Learning for Neural Video Compression 30 Nov 2024 · 0 repositories · arXiv:2412.00446
-
A Late-Stage Bitemporal Feature Fusion Network for Semantic Change Detection 15 Jun 2024 · 1 repository · arXiv:2406.10678
-
Real Time Egocentric Segmentation for Video-self Avatar in Mixed Reality 4 Jul 2022 · 0 repositories · arXiv:2207.01296
-
CE-FPN: Enhancing Channel Information for Object Detection 19 Mar 2021 · 1 repository · arXiv:2103.10643
-
Egocentric Human Segmentation for Mixed Reality 25 May 2020 · 0 repositories · arXiv:2005.12074
-
ThunderNet: Towards Real-Time Generic Object Detection on Mobile Devices 1 Oct 2019 · 0 repositories
-
AFP-Net: Realtime Anchor-Free Polyp Detection in Colonoscopy 5 Sep 2019 · 0 repositories · arXiv:1909.02477
-
ThunderNet: Towards Real-time Generic Object Detection 28 Mar 2019 · 3 repositories · arXiv:1903.11752
Tasks archive 2025-07-28
14 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections