Papers › Center and Scale Prediction: Anchor-free Approach for Pedestrian and Face Detection

Center and Scale Prediction: Anchor-free Approach for Pedestrian and Face Detection

5 Apr 2019CVPR 2019 6arXiv:1904.02948archive 2025-07-28

Wei Liu, Irtiza Hasan, Shengcai Liao

Object detection generally requires sliding-window classifiers in tradition or anchor box based predictions in modern deep learning approaches. However, either of these approaches requires tedious configurations in boxes. In this paper, we provide a new perspective where detecting objects is motivated as a high-level semantic feature detection task. Like edges, corners, blobs and other feature detectors, the proposed detector scans for feature points all over the image, for which the convolution is naturally suited. However, unlike these traditional low-level features, the proposed detector goes for a higher-level abstraction, that is, we are looking for central points where there are objects, and modern deep models are already capable of such a high-level semantic abstraction. Besides, like blob detection, we also predict the scales of the central points, which is also a straightforward convolution. Therefore, in this paper, pedestrian and face detection is simplified as a straightforward center and scale prediction task through convolutions. This way, the proposed method enjoys a box-free setting. Though structurally simple, it presents competitive accuracy on several challenging benchmarks, including pedestrian detection and face detection. Furthermore, a cross-dataset evaluation is performed, demonstrating a superior generalization ability of the proposed method. Code and models can be accessed at (https://github.com/liuwei16/CSP and https://github.com/hasanirtiza/Pedestron).

PaperPDFCode

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

Code

hasanirtiza/Pedestron officialmentioned in paperpytorchApache-2.0 report
liuwei16/CSP officialmentioned in papertf 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

Face DetectionObject DetectionPedestrian Detectionobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Pedestrian Detection Caltech CSP + CityPersons dataset Reasonable Miss Rate 3.8 #8 of 33 Archive leaderboard report
Pedestrian Detection Caltech CSP Reasonable Miss Rate 4.5 #11 of 33 Archive leaderboard report
Pedestrian Detection CityPersons CSP (with offset) + ResNet-50 Bare MR^-2 7.3 #14 of 22 Archive leaderboard report
Pedestrian Detection CityPersons CSP (with offset) + ResNet-50 Heavy MR^-2 49.3 #14 of 22 Archive leaderboard report
Pedestrian Detection CityPersons CSP (with offset) + ResNet-50 Large MR^-2 6.5 #14 of 22 Archive leaderboard report
Pedestrian Detection CityPersons CSP (with offset) + ResNet-50 Medium MR^-2 3.7 #14 of 22 Archive leaderboard report
Pedestrian Detection CityPersons CSP (with offset) + ResNet-50 Partial MR^-2 10.4 #14 of 22 Archive leaderboard report
Pedestrian Detection CityPersons CSP (with offset) + ResNet-50 Reasonable MR^-2 11.0 #14 of 22 Archive leaderboard report
Pedestrian Detection CityPersons CSP (with offset) + ResNet-50 Small MR^-2 16.0 #14 of 22 Archive leaderboard report
Pedestrian Detection CityPersons CSP (with offset) + ResNet-50 Test Time 0.33s/img #14 of 22 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

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionGlobal Average PoolingKaiming InitializationMax PoolingReLUResidual BlockResidual Connection

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