Convolutional Channel Features
This addresses the need for efficient and adaptable visual recognition methods for computer vision practitioners, though it is incremental as it integrates existing techniques.
The paper tackles the problem of expensive computation and limited flexibility in deep learning by proposing Convolutional Channel Features (CCF), which combines pre-trained CNN features with a boosting forest model, achieving state-of-the-art performances in tasks like pedestrian detection, face detection, edge detection, and object proposal generation.
Deep learning methods are powerful tools but often suffer from expensive computation and limited flexibility. An alternative is to combine light-weight models with deep representations. As successful cases exist in several visual problems, a unified framework is absent. In this paper, we revisit two widely used approaches in computer vision, namely filtered channel features and Convolutional Neural Networks (CNN), and absorb merits from both by proposing an integrated method called Convolutional Channel Features (CCF). CCF transfers low-level features from pre-trained CNN models to feed the boosting forest model. With the combination of CNN features and boosting forest, CCF benefits from the richer capacity in feature representation compared with channel features, as well as lower cost in computation and storage compared with end-to-end CNN methods. We show that CCF serves as a good way of tailoring pre-trained CNN models to diverse tasks without fine-tuning the whole network to each task by achieving state-of-the-art performances in pedestrian detection, face detection, edge detection and object proposal generation.