AI Paper Atlas

Research map / Detection and segmentation / CNN features

Funnel Activation for Visual Recognition

Ningning Ma, Xiangyu Zhang, Jian Sun

ECCV 2020 · Detection and segmentation › CNN features · approach: Convolution-transformer backbones · 120 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 ReLU with FReLUResNet-50 · ImageNet 2012 valtop-1 error (%): 24.0 -> 22.4Improved
replace ReLU with FReLUResNet-101 · ImageNet 2012 valtop-1 error (%): 22.8 -> 22.1Improved
replace ReLU with FReLUShuffleNetV2 · ImageNet 2012 valtop-1 error (%): 39.6 -> 37.1Improved
use FReLU backbone instead of ReLURetinaNet ResNet-50 · COCO minivalmAP: 35.2 -> 36.6Improved
use FReLU backbone instead of ReLUPSPNet ResNet-50 · Cityscapes valmean IU: 77.2 -> 78.9Improved
use parametric pooling instead of max pooling in the funnel condition (ablation)FReLU · ImageNet 2012 valtop-1 error (%): 24.4 -> 22.4Improved
use parametric pooling instead of average pooling in the funnel condition (ablation)FReLU · ImageNet 2012 valtop-1 error (%): 24.5 -> 22.4Improved
combine spatial condition and non-linearity with max rather than sum (ablation)FReLU · ImageNet 2012 valtop-1 error (%): 23.6 -> 22.4Improved
add max non-linearity on top of the spatial condition (vs depth-wise conv then ReLU) (ablation)FReLU · ImageNet 2012 valtop-1 error (%): 23.7 -> 22.4Improved
use 3x3 window instead of 1x1 (PReLU case) (ablation)FReLU · ImageNet 2012 valtop-1 error (%): 23.7 -> 22.4Improved
use 3x3 window instead of 5x5 or 7x7 (ablation)FReLU · ImageNet 2012 valtop-1 error (%): 22.9 -> 22.4Improved
apply FReLU after both 1x1 and 3x3 convs instead of one (ablation)FReLU · ImageNet 2012 valtop-1 error (%): 22.9 -> 22.4Improved

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