Cascaded Sparse Spatial Bins for Efficient and Effective Generic Object Detection
arXiv:1504.07029
Abstract
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.
arXiv commentAccepted to ICCV15
References in corpus (8)
- Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
- OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks
- What makes for effective detection proposals?
- Rich feature hierarchies for accurate object detection and semantic segmentation
- Scalable, High-Quality Object Detection
- How good are detection proposals, really?
- Boosting Convolutional Features for Robust Object Proposals
- Understanding the Fisher Vector: a multimodal part model