ComputingComputer ScienceComputer VisionMachine LearningMachine VisionDeep LearningImage ClassificationObject DetectionObject RecognitionPattern RecognitionScene UnderstandingAccuracyConvolutional Neural Network DetectionConvolutional Neural NetworksObject ClassificationRegion Proposal Networks
Fast R‑CNN builds on prior work to efficiently classify object proposals with deep convolutional networks. The paper proposes Fast R‑CNN, a region‑based convolutional network that improves training and testing speed while increasing detection accuracy for object detection. Fast R‑CNN uses a novel training pipeline implemented in Python and C++ with Caffe, incorporating innovations that accelerate training and testing while remaining open source. Fast R‑CNN trains VGG16 nine times faster than R‑CNN, tests 213 times faster, and attains higher mAP on PASCAL VOC 2012, outperforming SPPnet with three‑fold faster training, ten‑fold faster testing, and better accuracy.
This paper proposes a Fast Region-based Convolutional Network method (Fast R-CNN) for object detection. Fast R-CNN builds on previous work to efficiently classify object proposals using deep convolutional networks. Compared to previous work, Fast R-CNN employs several innovations to improve training and testing speed while also increasing detection accuracy. Fast R-CNN trains the very deep VGG16 network 9x faster than R-CNN, is 213x faster at test-time, and achieves a higher mAP on PASCAL VOC 2012. Compared to SPPnet, Fast R-CNN trains VGG16 3x faster, tests 10x faster, and is more accurate. Fast R-CNN is implemented in Python and C++ (using Caffe) and is available under the open-source MIT License at this https URL.
23
ImageNet: A large-scale hierarchical image database
Jia Deng, Wei Dong, Richard Socher et al. · 2009 IEEE Conference on Computer Vision and Pattern Recognition · 2009 · 61.8K citations
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
Ross Girshick, Jeff Donahue, Trevor Darrell et al. · 2014 · 31.8K citations
The Pascal Visual Object Classes (VOC) Challenge
Mark Everingham, Luc Van Gool, Christopher K. I. Williams et al. · International Journal of Computer Vision · 2009 · 19.5K citations · Full text