Learning Complexity-Aware Cascades for Deep Pedestrian Detection

TL;DR

This paper introduces a complexity-aware cascade learning method, CompACT, that optimally balances accuracy and computational complexity, enabling the integration of complex features like deep CNN responses into pedestrian detection.

Contribution

The paper proposes a new cascade design and training algorithm, CompACT, that effectively combines features of varying complexities, including deep CNN responses, for improved pedestrian detection.

Findings

Achieved state-of-the-art pedestrian detection performance.

Effectively integrated deep CNN features into cascade detection.

Demonstrated fast detection speeds on benchmark datasets.

Abstract

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.