AI Paper Atlas

Research map / Detection and segmentation / CNN features

Rethinking Spatial Invariance of Convolutional Networks for Object Counting

Zhi-Qi Cheng, Qi Dai, Hong Li, Jingkuan Song, Xiao Wu, Alexander G. Hauptmann

CVPR 2022 · Detection and segmentation › CNN features · approach: Local features and context in CNNs · 122 citations (OpenAlex)

Check 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 convolution filters with low-rank Gaussian convolutions in ResNet-50ResNet-50 · SHTech-PartAMAE: 55.4 -> 54.8Improved
replace convolution filters with low-rank Gaussian convolutions in ResNet-50ResNet-50 · UCF_CC_50MAE: 197.5 -> 186.3Improved
replace convolution filters with low-rank Gaussian convolutions in CSRNetCSRNet · UCF-QNRFMAE: 71.3 -> 84.2Hurt
replace convolution filters with low-rank Gaussian convolutions in ResNet-50ResNet-50 · JHU-CROWD++MAE: 59.9 -> 58.2Improved
replace convolution filters with low-rank Gaussian convolutions in ResNet-50ResNet-50 · SHTech-PartBMAE: 6.4 -> 6.2Improved
replace convolution filters with low-rank Gaussian convolutions in ResNet-50ResNet-50 · TRANCOSMAE: 2.6 -> 2.1Improved
replace convolution filters with low-rank Gaussian convolutions in ResNet-50ResNet-50 · MTCMAE: 5.6 -> 3.1Improved
add low-rank approximation to Gaussian convolution (ablation)Gaussian convolution on MCNN · MCNN, batchsize 1 and image size 256²forward time (milliseconds): 51.3 -> 13.3Improved
add translation invariance to low-rank Gaussian convolution (ablation)LRA on MCNN · MCNN, batchsize 1 and image size 256²forward time (milliseconds): 13.3 -> 4.1Improved
add low-rank approximation to Gaussian convolution (ablation)Gaussian convolution on MCNN · MCNN, batchsize 1 and image size 256²backward time (milliseconds): 160.0 -> 44.1Improved
add translation invariance to low-rank Gaussian convolution (ablation)LRA on MCNN · MCNN, batchsize 1 and image size 256²backward time (milliseconds): 44.1 -> 12.6Improved
use larger K in spatial pyramid pooling (ablation)GauNet in MCNN and SANet · MCNN and SANet spatial pyramid poolingcounting performanceMixed

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