Adapted Center and Scale Prediction: More Stable and More Accurate

20 Feb 2020  ·  Wenhao Wang ·

Pedestrian detection benefits from deep learning technology and gains rapid development in recent years. Most of detectors follow general object detection frame, i.e. default boxes and two-stage process. Recently, anchor-free and one-stage detectors have been introduced into this area. However, their accuracies are unsatisfactory. Therefore, in order to enjoy the simplicity of anchor-free detectors and the accuracy of two-stage ones simultaneously, we propose some adaptations based on a detector, Center and Scale Prediction(CSP). The main contributions of our paper are: (1) We improve the robustness of CSP and make it easier to train. (2) We propose a novel method to predict width, namely compressing width. (3) We achieve the second best performance on CityPersons benchmark, i.e. 9.3% log-average miss rate(MR) on reasonable set, 8.7% MR on partial set and 5.6% MR on bare set, which shows an anchor-free and one-stage detector can still have high accuracy. (4) We explore some capabilities of Switchable Normalization which are not mentioned in its original paper.

PDF Abstract

Datasets


Results from the Paper


 Ranked #1 on Pedestrian Detection on CityPersons (Bare MR^-2 metric, using extra training data)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
Pedestrian Detection CityPersons ACSP + EuroCity Persons Heavy MR^-2 42.5 # 8
Partial MR^-2 6.9 # 2
Bare MR^-2 4.9 # 1
Pedestrian Detection CityPersons ACSP Reasonable MR^-2 9.3 # 7
Heavy MR^-2 46.3 # 10
Partial MR^-2 8.7 # 3
Bare MR^-2 5.6 # 2

Methods