Papers › CARAFE: Content-Aware ReAssembly of FEatures

CARAFE: Content-Aware ReAssembly of FEatures

6 May 2019ICCV 2019 10arXiv:1905.02188archive 2025-07-28

Jiaqi Wang, Kai Chen, Rui Xu, Ziwei Liu, Chen Change Loy, Dahua Lin

Feature upsampling is a key operation in a number of modern convolutional network architectures, e.g. feature pyramids. Its design is critical for dense prediction tasks such as object detection and semantic/instance segmentation. In this work, we propose Content-Aware ReAssembly of FEatures (CARAFE), a universal, lightweight and highly effective operator to fulfill this goal. CARAFE has several appealing properties: (1) Large field of view. Unlike previous works (e.g. bilinear interpolation) that only exploit sub-pixel 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. CARAFE introduces little computational overhead and can be readily integrated into modern network architectures. We conduct comprehensive evaluations on standard benchmarks in object detection, instance/semantic segmentation and inpainting. CARAFE shows consistent and substantial gains across all the tasks (1.2%, 1.3%, 1.8%, 1.1db respectively) with negligible computational overhead. It has great potential to serve as a strong building block for future research. It has great potential to serve as a strong building block for future research. Code and models are available at https://github.com/open-mmlab/mmdetection.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

open-mmlab/mmdetection mentioned in paperpytorchApache-2.0 report
smallsunsun1/custom_ops mentioned on GitHubtf report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Feature UpsamplingInstance SegmentationObject DetectionSemantic Segmentationobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Feature Upsampling ImageNet CARAFE ADCC 59.7 #5 of 8 Archive leaderboard report
Feature Upsampling ImageNet CARAFE Average Drop 49.9 #5 of 8 Archive leaderboard report
Feature Upsampling ImageNet CARAFE Average Increase 4.8 #5 of 8 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Introduced by this paper: CARAFE

CARAFE

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