Are Sampling Heuristics Necessary in Object Detectors?

Keywords

Computer science, Sampling (signal processing), Heuristics, Artificial intelligence, Pascal (unit)

References

• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick — 2015
• You Only Look Once: Unified, Real-Time Object DetectionJoseph Redmon, Santosh Divvala, Ross Girshick — 2015
• Cascade object detection with deformable part modelsPedro F. Felzenszwalb, Ross Girshick, David McAllester — 2010
• Selective Search for Object RecognitionJasper Uijlings, Koen E. A. van de Sande, Theo Gevers — 2013
• RUSBoost: A Hybrid Approach to Alleviating Class ImbalanceChris Seiffert, Taghi M. Khoshgoftaar, Jason Van Hulse — 2010
• A Review on Ensembles for the Class Imbalance Problem: Bagging-, Boosting-, and Hybrid-Based ApproachesMikel Galar, Alberto Fernández, Edurne Barrenechea — 2012
• Rich Feature Hierarchies for Accurate Object Detection and Semantic SegmentationRoss Girshick, Jeff Donahue, Trevor Darrell — 2013
• Learning When Data Sets are Imbalanced and When Costs are Unequal and UnknownMarcus A. Maloof — 2003
• DenseBox: Unifying Landmark Localization with End to End Object DetectionLichao Huang, Yi Yang, Yafeng Deng — 2015
• Robust Real-Time Face DetectionPaul Viola, Michael Jones — 2001
• SMOTE: Synthetic Minority Over-sampling TechniqueNitesh V. Chawla, Kevin W. Bowyer, Lawrence Hall — 2002
• ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton — 2012
• Deep Residual Learning for Image RecognitionKaiming He, Xiangyu Zhang, Shaoqing Ren — 2015
• Training Region-Based Object Detectors with Online Hard Example MiningAbhinav Shrivastava, Abhinav Gupta, Ross Girshick — 2016
• R-FCN: Object Detection via Region-based Fully Convolutional NetworksJifeng Dai, Yi Li, Kaiming He — 2016
• Aggregated Residual Transformations for Deep Neural NetworksSaining Xie, Ross Girshick, Piotr Dollár — 2016
• Feature Pyramid Networks for Object DetectionTsung-Yi Lin, Piotr Dollár, Ross Girshick — 2016
• YOLO9000: Better, Faster, StrongerJoseph Redmon, Ali Farhadi — 2016
• Multi-task Learning Using Uncertainty to Weigh Losses for Scene Geometry and SemanticsAlex Kendall, Yarin Gal, Roberto Cipolla — 2017
• RON: Reverse Connection with Objectness Prior Networks for Object DetectionTao Kong, Fuchun Sun, Anbang Yao — 2017

Cited by

No citing papers recorded for this paper.

Related papers

• Is Sampling Heuristics Necessary in Training Deep Object DetectorsJoya Chen, Dong Liu, Tong Xu — 2019
• Revisiting Foreground-Background Imbalance in Object DetectorsJoya Chen, Dong Liu, Tong Xu — 2019
• Is Heuristic Sampling Necessary in Training Deep Object Detectors?Joya Chen, Dong Liu, Tong Xu — 2019
• Margin-based Sampling in Deep Metric LearningShangwei Zhou, Qingsong Yu, Jun Sun — 2019
• LapNet : Automatic Balanced Loss and Optimal Assignment for Real-Time Dense Object DetectionFlorian Chabot, Pham, Quoc-Cuong, Mohamed Chaouch — 2019
• Towards Accurate One-Stage Object Detection With AP-LossKean Chen, Jianguo Li, Weiyao Lin — 2019
• Deep Active Learning for Object Detection with Mixture Density NetworksJi-Woong Choi, Ismail Elezi, Hyuk‐Jae Lee — 2021
• Pedestrian detection with dynamic iterative bootstrappingChao Pei, Lei Hao, Yuesheng Zhu — 2017