Co-training of context models for real-time vehicle detection

Abstract

We describe a simple way to reduce the amount of required training data in context-based models of realtime object detection. We demonstrate the feasibility of our approach in a very challenging vehicle detection scenario comprising multiple weather, environment and light conditions such as rain, snow and darkness (night). The investigation is based on a real-time detection system effectively composed of two trainable components: an exhaustive multiscale object detector ("signal-driven detection"), as well as a module for generating object-specific visual attention ("context models") controlling the signal-driven detection process. Both parts of the system require a significant amount of ground-truth data which need to be generated by human annotation in a time-consuming and costly process.Assuming sufficient training examples for signal-based detection, we demonstrate that a co-training step can eliminate the need for separate ground-truth data to train context models. This is achieved by directly training context models with the results of signal-driven detection. We show that this process is feasible for different qualities of signal-driven detection, and maintains the performance gains from context models.As it is by now widely accepted that signal-driven object detection can be significantly improved by context models, our method allows to train strongly improved detection systems without additional labor, and above all, cost.

Cooperative Learning and its Application to Emotion Recognition from Speech

“…MVL techniques in general are less restrictive than Co-Training in particular and can be applied with two or more views on the data and with less restrictive conditions in terms of conditional independence. MVL schemes have been applied in several areas, such as biometrics [26], intelligent transportation [27], and handwriting [28] classication. In emotion recognition from acoustic signals, they have also been successfully applied with relevant improvements over Self-Training [29], [30].…”

Co-training succeeds in Computational Paralinguistics

“…For human action recognition, in [25] a boosted co-training algorithm is proposed, where inter-view and intra-view confidence addresses the view-sufficiency and dependence issues in co-training. In addition, co-training is also researched in on-line biometrics [26], music mood [27], vehicle [28], and handwritten word [29] classification.…”