Learning Complexity-Aware Cascades for Deep Pedestrian Detection
This work addresses the challenge of integrating features with vastly different complexities, such as deep CNNs, into cascaded detectors for pedestrian detection, which is incremental but improves efficiency and accuracy.
The paper tackles the problem of designing efficient pedestrian detectors by introducing a complexity-aware cascade learning method that optimizes the trade-off between accuracy and computational cost, achieving state-of-the-art performance on Caltech and KITTI datasets with fast speeds.
The design of complexity-aware cascaded detectors, combining features of very different complexities, is considered. A new cascade design procedure is introduced, by formulating cascade learning as the Lagrangian optimization of a risk that accounts for both accuracy and complexity. A boosting algorithm, denoted as complexity aware cascade training (CompACT), is then derived to solve this optimization. CompACT cascades are shown to seek an optimal trade-off between accuracy and complexity by pushing features of higher complexity to the later cascade stages, where only a few difficult candidate patches remain to be classified. This enables the use of features of vastly different complexities in a single detector. In result, the feature pool can be expanded to features previously impractical for cascade design, such as the responses of a deep convolutional neural network (CNN). This is demonstrated through the design of a pedestrian detector with a pool of features whose complexities span orders of magnitude. The resulting cascade generalizes the combination of a CNN with an object proposal mechanism: rather than a pre-processing stage, CompACT cascades seamlessly integrate CNNs in their stages. This enables state of the art performance on the Caltech and KITTI datasets, at fairly fast speeds.