Adapted Center and Scale Prediction: More Stable and More Accurate
share
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 achieve the second best performance on the CityPersons benchmark, which shows an anchor-free and one-stage detector can still have high accuracy. (3) We explore some extra capabilities of recently proposed normalization method, Switchable Normalization.
READ FULL TEXT