Methods › Computer Vision › Feature Upsampling › CARAFE

CARAFE

6 papers tagged archive 2025-07-28

Introduced by Jiaqi Wang et al. in CARAFE: Content-Aware ReAssembly of FEatures

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

Content-Aware ReAssembly of FEatures (CARAFE) is an operator for feature upsampling in convolutional neural networks. CARAFE has several appealing properties: (1) Large field of view. Unlike previous works (e.g. bilinear interpolation) that only exploit subpixel neighborhood, CARAFE can aggregate contextual information within a large receptive field. (2) Content-aware handling. Instead of using a fixed kernel for all samples (e.g. deconvolution), CARAFE enables instance-specific content-aware handling, which generates adaptive kernels on-the-fly. (3) Lightweight and fast to compute.

Paper Source

Papers archive 2025-07-28

6 shown of 6, 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.

CCi-YOLOv8n: Enhanced Fire Detection with CARAFE and Context-Guided Modules
17 Nov 2024 · 0 repositories · arXiv:2411.11011
Lighten CARAFE: Dynamic Lightweight Upsampling with Guided Reassemble Kernels
29 Oct 2024 · 1 repository · arXiv:2410.22139
IDD-YOLOv5: A Lightweight Insulator Defect Real-time Detection Algorithm
19 Aug 2024 · 1 repository
Learning to Upsample by Learning to Sample
29 Aug 2023 · 1 repository · arXiv:2308.15085

Syntology ran 1 of 1 samples · 0 unverified
On the impact of using X-ray energy response imagery for object detection via Convolutional Neural Networks
27 Aug 2021 · 0 repositories · arXiv:2108.12505
CARAFE: Content-Aware ReAssembly of FEatures
6 May 2019 · 3 repositories · arXiv:1905.02188

Tasks archive 2025-07-28

15 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

Task	Papers
Object Detection	5
object-detection	4
Feature Upsampling	3
Instance Segmentation	2
Semantic Segmentation	2
Defect Detection	1
Depth Estimation	1
Fire Detection	1
GPU	1
Insulator Defect Detection	1
Monocular Depth Estimation	1
Object	1
Panoptic Segmentation	1
Segmentation	1
Small Object Detection	1

Usage over time archive 2025-07-28

Papers per year the archive tags with this method, by the paper's archive date (6 dated). Bars are counts, not a trend claim.

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

Feature Upsampling

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