PFDet: 2nd Place Solution to Open Images Challenge 2018 Object Detection Track
arXiv:1809.00778
Abstract
We present a large-scale object detection system by team PFDet. Our system enables training with huge datasets using 512 GPUs, handles sparsely verified classes, and massive class imbalance. Using our method, we achieved 2nd place in the Google AI Open Images Object Detection Track 2018 on Kaggle.
Technical report for Open Images Challenge 2018 Object Detection Track
References in corpus (5)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour
- Extremely Large Minibatch SGD: Training ResNet-50 on ImageNet in 15 Minutes
- ChainerMN: Scalable Distributed Deep Learning Framework
- ChainerCV: a Library for Deep Learning in Computer Vision
Cited by in corpus (10)
- 1st Place Solutions for OpenImage2019 -- Object Detection and Instance Segmentation
- The Case for Strong Scaling in Deep Learning: Training Large 3D CNNs with Hybrid Parallelism
- 1st Place Solutions of Waymo Open Dataset Challenge 2020 -- 2D Object Detection Track
- Learning Effective Visual Relationship Detector on 1 GPU
- 1st place solution for AVA-Kinetics Crossover in AcitivityNet Challenge 2020
- Large-Scale Object Detection in the Wild from Imbalanced Multi-Labels
- Scaling Object Detection by Transferring Classification Weights
- Learning an Efficient Network for Large-Scale Hierarchical Object Detection with Data Imbalance: 3rd Place Solution to Open Images Challenge 2019
- Team PFDet's Methods for Open Images Challenge 2019
- Decoupled Gradient Harmonized Detector for Partial Annotation: Application to Signet Ring Cell Detection