Fast Learning and Prediction for Object Detection using Whitened CNN Features
This work addresses the need for real-time object detection with minimal training data, though it appears incremental as it integrates existing methods.
The paper tackles the problem of achieving high detection performance with fast learning and prediction by combining pre-trained CNN features with the linear Exemplar-LDA classifier, resulting in efficient sliding-window detection and fast model learning from few samples.
We combine features extracted from pre-trained convolutional neural networks (CNNs) with the fast, linear Exemplar-LDA classifier to get the advantages of both: the high detection performance of CNNs, automatic feature engineering, fast model learning from few training samples and efficient sliding-window detection. The Adaptive Real-Time Object Detection System (ARTOS) has been refactored broadly to be used in combination with Caffe for the experimental studies reported in this work.