1st Place Solutions of Waymo Open Dataset Challenge 2020 -- 2D Object Detection Track

Abstract

In this technical report, we present our solutions of Waymo Open Dataset (WOD) Challenge 2020 - 2D Object Track. We adopt FPN as our basic framework. Cascade RCNN, stacked PAFPN Neck and Double-Head are used for performance improvements. In order to handle the small object detection problem in WOD, we use very large image scales for both training and testing. Using our methods, our team RW-TSDet achieved the 1st place in the 2D Object Detection Track.

References in corpus (9)

• Distilling the Knowledge in a Neural Network
• Res2Net: A New Multi-scale Backbone Architecture
• Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour
• SGDR: Stochastic Gradient Descent with Warm Restarts
• MMDetection: Open MMLab Detection Toolbox and Benchmark
• Path Aggregation Network for Instance Segmentation
• Deep High-Resolution Representation Learning for Visual Recognition
• Scalability in Perception for Autonomous Driving: Waymo Open Dataset
• PFDet: 2nd Place Solution to Open Images Challenge 2018 Object Detection Track

Cited by in corpus (2)

• USB: Universal-Scale Object Detection Benchmark
• Towards Fine-grained Large Object Segmentation 1st Place Solution to 3D AI Challenge 2020 -- Instance Segmentation Track