Cascaded Sparse Spatial Bins for Efficient and Effective Generic Object Detection
This work addresses the problem of computational efficiency and accuracy in object detection for computer vision applications, offering incremental improvements over existing methods.
The paper tackles efficient generic object detection by introducing a novel object proposal extraction method that combines deep spatial pyramid features, a fast HoG-based edge statistic, and EdgeBoxes score, achieving state-of-the-art recall on Pascal VOC07 with 78% recall using only 100 proposals and improving RCNN mAP by 10 points with 50 proposals.
A novel efficient method for extraction of object proposals is introduced. Its "objectness" function exploits deep spatial pyramid features, a novel fast-to-compute HoG-based edge statistic and the EdgeBoxes score. The efficiency is achieved by the use of spatial bins in a novel combination with sparsity-inducing group normalized SVM. State-of-the-art recall performance is achieved on Pascal VOC07, significantly outperforming methods with comparable speed. Interestingly, when only 100 proposals per image are considered the method attains 78% recall on VOC07. The method improves mAP of the RCNN state-of-the-art class-specific detector, increasing it by 10 points when only 50 proposals are used in each image. The system trained on twenty classes performs well on the two hundred class ILSVRC2013 set confirming generalization capability.