Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation

@article{Girshick2014RichFH,
  title={Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation},
  author={Ross B. Girshick and Jeff Donahue and Trevor Darrell and J. Malik},
  journal={2014 IEEE Conference on Computer Vision and Pattern Recognition},
  year={2014},
  pages={580-587}
}
Object detection performance, as measured on the canonical PASCAL VOC dataset, has plateaued in the last few years. [...] Key Method 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.Expand
View on IEEE
arxiv.org
14,313 Citations
Highly Influential Citations
2,099
Background Citations
5,106
Methods Citations
5,712
Results Citations
130

14,313 Citations

Citation Type

Citation Type

Region-Based Convolutional Networks for Accurate Object Detection and Segmentation
Improve object detection via a multi-feature and multi-task CNN model
Boosting Convolutional Features for Robust Object Proposals
CNN based region proposals for efficient object detection
Object Detection via a Multi-region and Semantic Segmentation-Aware CNN Model
Simultaneous Detection and Segmentation
Object proposals using CNN-based edge filtering
Convolutional Oriented Boundaries: From Image Segmentation to High-Level Tasks
Exploit Bounding Box Annotations for Multi-Label Object Recognition
Semi-supervised exemplar learning for object detection in aerial imagery
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 64 REFERENCES
Learning Hierarchical Features for Scene Labeling
Regionlets for Generic Object Detection
Bottom-Up Segmentation for Top-Down Detection
Semantic segmentation using regions and parts
OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks
Boosted local structured HOG-LBP for object localization
Measuring the Objectness of Image Windows
CPMC: Automatic Object Segmentation Using Constrained Parametric Min-Cuts
Deep Neural Networks for Object Detection
The Pascal Visual Object Classes (VOC) Challenge
...
1
2
3
4
5
...