Title | ||
---|---|---|
R-FCN plus plus : Towards Accurate Region-Based Fully Convolutional Networks for Object Detection |
Abstract | ||
---|---|---|
Region based detectors like Faster R-CNN (Ren et al. 2015) and R-FCN (Li et al. 2016) have achieved leading performance on object detection benchmarks. However, in Faster R-CNN, RoI pooling is used to extract feature of each region, which might harm the classification as the RoI pooling loses spatial resolution. Also it gets slow when a large number of proposals are utilized. R-FCN is a fully convolutional structure that uses a position-sensitive pooling layer to extract prediction score of each region, which speeds up network by sharing computation of RoIs and prevents the feature map from losing information in RoI-pooling. But R-FCN can not benefit from fully connected layer (or global average pooling), which enables Faster R-CNN to utilize global context information. In this paper, we propose R-FCN++ to address this issue in two-fold: first we involve Global Context Module to improve the classification score maps by adopting large, separable convolutional kernels. Second we introduce a new pooling method to better extract scores from the score maps, by using row-wise or column-wise max pooling. Our approach achieves state-of-the-art single-model results on both Pascal VOC and MS COCO object detection benchmarks, 87.3% on Pascal VOC 2012 test dataset and 42.3% on COCO 2015 test-dev dataset. Code will be made publicly available. |
Year | Venue | Field |
---|---|---|
2018 | AAAI | Computer vision,Object detection,Computer science,Artificial intelligence,Machine learning |
DocType | Citations | PageRank |
Conference | 2 | 0.37 |
References | Authors | |
0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Zeming Li | 1 | 32 | 2.85 |
Yilun Chen | 2 | 7 | 0.77 |
Gang Yu | 3 | 382 | 19.85 |
Yangdong Deng | 4 | 429 | 44.78 |