Papers › Rethinking Spatial Invariance of Convolutional Networks for Object Counting

Rethinking Spatial Invariance of Convolutional Networks for Object Counting

10 Jun 2022CVPR 2022 1arXiv:2206.05253archive 2025-07-28

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

Previous work generally believes that improving the spatial invariance of convolutional networks is the key to object counting. However, after verifying several mainstream counting networks, we surprisingly found too strict pixel-level spatial invariance would cause overfit noise in the density map generation. In this paper, we try to use locally connected Gaussian kernels to replace the original convolution filter to estimate the spatial position in the density map. The purpose of this is to allow the feature extraction process to potentially stimulate the density map generation process to overcome the annotation noise. Inspired by previous work, we propose a low-rank approximation accompanied with translation invariance to favorably implement the approximation of massive Gaussian convolution. Our work points a new direction for follow-up research, which should investigate how to properly relax the overly strict pixel-level spatial invariance for object counting. We evaluate our methods on 4 mainstream object counting networks (i.e., MCNN, CSRNet, SANet, and ResNet-50). Extensive experiments were conducted on 7 popular benchmarks for 3 applications (i.e., crowd, vehicle, and plant counting). Experimental results show that our methods significantly outperform other state-of-the-art methods and achieve promising learning of the spatial position of objects.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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

Code

zhiqic/rethinking-counting officialmentioned in papermentioned on GitHubpytorch 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

Crowd CountingObjectObject Counting

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Crowd Counting JHU-CROWD++ GauNet (ResNet-50) MAE 58.2 #2 of 3 Archive leaderboard report
Crowd Counting JHU-CROWD++ GauNet (ResNet-50) MSE 245.1 #2 of 3 Archive leaderboard report
Crowd Counting ShanghaiTech A GauNet (ResNet-50) MAE 54.8 #9 of 35 Archive leaderboard report
Crowd Counting ShanghaiTech A GauNet (ResNet-50) MSE 89.1 #9 of 35 Archive leaderboard report
Crowd Counting ShanghaiTech B GauNet (ResNet-50) MAE 6.0 #5 of 32 Archive leaderboard report
Crowd Counting UCF CC 50 GauNet (ResNet-50) MAE 186.3 #3 of 22 Archive leaderboard report
Crowd Counting UCF-QNRF GauNet (ResNet-50) MAE 81.6 #9 of 23 Archive leaderboard report
Object Counting TRANCOS GauNet (ResNet-50) MAE 2.1 #1 of 1 Archive leaderboard report
Object Counting TRANCOS GauNet (ResNet-50) MSE 2.6 #1 of 1 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

Convolution

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