R-CNN
Source code for the complete system is available at http://www.cs.berkeley.edu/~rbg/rcnn. Ross Girshick, et al., "Rich feature hierarchies for accurate object detection and semantic segmentation" https://arxiv.org/abs/1311.2524 物体検出に…
We find that R-CNN outperforms OverFeat by a large margin on the 200-class ILSVRC2013 detection dataset. Ross Girshick, et al., "Rich feature hierarchies for accurate object detection and semantic segmentation" https://arxiv.org/abs/1311.2…
We also compare R-CNN to OverFeat, a recently proposed sliding-window detector based on a similar CNN architecture. Ross Girshick, et al., "Rich feature hierarchies for accurate object detection and semantic segmentation" https://arxiv.org…
Since we combine region proposals with CNNs, we call our method R-CNN: Regions with CNN features. Ross Girshick, et al., "Rich feature hierarchies for accurate object detection and semantic segmentation" https://arxiv.org/abs/1311.2524 物…
Our approach combines two key insights: (1) one can apply high-capacity convolutional neural networks (CNNs) to bottom-up region proposals in order to localize and segment objects and (2) when labeled training data is scarce, supervised pr…
In this paper, we propose a simple and scalable detection algorithm that improves mean average precision (mAP) by more than 30% relative to the previous best result on VOC 2012—achieving a mAP of 53.3%. Ross Girshick, et al., "Rich feature…
The best-performing methods are complex ensemble systems that typically combine multiple low-level image features with high-level context. Ross Girshick, et al., "Rich feature hierarchies for accurate object detection and semantic segmenta…
Object detection performance, as measured on the canonical PASCAL VOC dataset, has plateaued in the last few years. Ross Girshick, et al., "Rich feature hierarchies for accurate object detection and semantic segmentation" https://arxiv.org…