AI Paper Atlas

Research map / Detection and segmentation / CNN features

CARAFE++: Unified Content-Aware ReAssembly of FEatures

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

TPAMI 2021 · Detection and segmentation › CNN features · approach: Joint detection and instance segmentation · 91 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace strided convolution downsampling in ResNet-50 with CARAFE++Faster R-CNN ResNet-50 FPN · COCO val (1x)AP box: 36.5 -> 38.8Improved
use CARAFE++ for downsampling instead of max pooling (ablation)Faster R-CNN ResNet-50 FPN · COCO val (1x)AP box: 37.8 -> 38.8Improved
replace nearest-neighbor upsampling in FPN with CARAFE++ (ablation)Faster R-CNN ResNet-50 FPN · COCO val (1x)AP box: 36.5 -> 37.8Improved
add an extra 3x3 conv after nearest or bilinear upsampling (ablation)Faster R-CNN FPN upsampling · COCO val (1x)AP box: 36.5 -> 36.6No clear effect
apply CARAFE++ in both backbone and FPN (ablation)Faster R-CNN ResNet-50 · COCO val (1x)AP box: 37.8 -> 39.6Improved
replace deconvolution in the mask head with CARAFE++ (ablation)Mask R-CNN ResNet-50 · COCO val (1x)AP mask: 34.2 -> 34.7Improved
apply CARAFE++ in FPN, mask head and backbone together (ablation)Mask R-CNN ResNet-50 · COCO val (1x)AP mask: 34.2 -> 36.8Improved
add CARAFE++ downsampling to ResNet backboneResNet-50 classification · ImageNet-1k valTop-1 accuracy: 76.43 -> 77.46Improved
add CARAFE++ to ResNet-101 with DCNv2 detectorFaster R-CNN ResNet-101-DCNv2 · COCO test-dev (2x)AP box: 43.2 -> 44.3Improved
add CARAFE++ to UperNet components PPM, FPN, FUSE and backboneUperNet ResNet-50 · ADE20k valmIoU: 40.44 -> 43.05Improved
add CARAFE++ backbone on top of PPM+FPN+FUSE (ablation)UperNet ResNet-50 · ADE20k valmIoU: 42.23 -> 43.05Improved
add CARAFE++ to Global&Local inpaintingGlobal&Local · Places valPSNR: 19.58 -> 20.93Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy