Adapted Center and Scale Prediction: More Stable and More Accurate
arXiv:2002.09053
Abstract
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. The code is publicly available at https://github.com/WangWenhao0716/Adapted-Center-and-Scale-Prediction.
14 pages, 7 figures
References in corpus (11)
- Adam: A Method for Stochastic Optimization
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- Instance Normalization: The Missing Ingredient for Fast Stylization
- Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
- CrowdHuman: A Benchmark for Detecting Human in a Crowd
- DenseBox: Unifying Landmark Localization with End to End Object Detection
- The EuroCity Persons Dataset: A Novel Benchmark for Object Detection
- Differentiable Learning-to-Normalize via Switchable Normalization
- Local Decorrelation For Improved Detection
- Semantic Head Enhanced Pedestrian Detection in a Crowd