Adapting detectors to new datasets is needed in scenarios where a user has a specific dataset that contains novel classes or is recorded in a setting where a pretrained detector fails. While detectors based on Convolutional Neural Networks (CNNs) are state-of-the-art and nowadays publicly available, they suffer from bad generalization capabilities when applied on datasets that notably differ from the one they were trained on. Finetuning the detector is only possible if the dataset is large enough to not destroy the underlying feature representation. We propose a method where only a few prototypes are labeled for training in a semi-supervised manner. In particular, we separate the detection from the classification step to avoid impairing the bounding box proposal generation. Our trained prototype classification network provides labels to automatically source a large dataset containing 20 to 30 times more samples without further supervision, which we then use to train a more powerful network. We evaluate our method on a private vehicle dataset with six classes and show that evaluating on a previously unseen recording site we can gain an accuracy increase of 9% at same precision and recall levels. We further show that finetuning with as few as 25 labeled samples per class doubles accuracy compared to directly using pretrained features for nearest neighbor classification.
Semi-supervised Detector Training with Prototypes for Vehicle Detection
2019-10-01
3075468 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Semi-Supervised Self-Training of Object Detection Models
IEEE | 2005
|Semi-Supervised Face Detection
IEEE | 2005
|Semi-Supervised Eigenbasis Novelty Detection
Online Contents | 2013
Deep Co-Training for Semi-Supervised Image Recognition
British Library Conference Proceedings | 2018
|