Rich feature hierarchies for accurate object detection and semantic segmentation

Code

• github.com/dineshzende/awesome-deep-learning-resources
  tf★ 6
• github.com/pmsharkKOR/Deep-Learning-Examples---Awesome-Resourse1
  tf★ 2
• github.com/jiangbestone/DetectRCNN
  pytorch★ 2
• github.com/polospeter/TensorFlow-Advanced-Techniques-Specialization
  tf★ 0
• github.com/cftang0827/pedestrian-detection-ssdlite
  tf★ 0
• github.com/Anmol6/capshun
  none★ 0
• github.com/jtiger958/pytorch-computer-vision-tutorial
  pytorch★ 0
• github.com/quocdat32461997/Mask_RCNN
  tf★ 0
• github.com/jiangbestone/DetectRccn
  pytorch★ 0
• github.com/s1ns11/FasterR-CNN
  pytorch★ 0

Abstract

Object detection performance, as measured on the canonical PASCAL VOC dataset, has plateaued in the last few years. The best-performing methods are complex ensemble systems that typically combine multiple low-level image features with high-level context. 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%. 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 pre-training for an auxiliary task, followed by domain-specific fine-tuning, yields a significant performance boost. Since we combine region proposals with CNNs, we call our method R-CNN: Regions with CNN features. We also compare R-CNN to OverFeat, a recently proposed sliding-window detector based on a similar CNN architecture. We find that R-CNN outperforms OverFeat by a large margin on the 200-class ILSVRC2013 detection dataset. Source code for the complete system is available at http://www.cs.berkeley.edu/~rbg/rcnn.

Tasks

Benchmark Results

Reproductions