DeepAI AI Chat
Log In Sign Up

1st Place Solutions for OpenImage2019 – Object Detection and Instance Segmentation

by   Yu Liu, et al.
SenseTime Corporation
The Chinese University of Hong Kong

This article introduces the solutions of the two champion teams, `MMfruit' for the detection track and `MMfruitSeg' for the segmentation track, in OpenImage Challenge 2019. It is commonly known that for an object detector, the shared feature at the end of the backbone is not appropriate for both classification and regression, which greatly limits the performance of both single stage detector and Faster RCNN <cit.> based detector. In this competition, we observe that even with a shared feature, different locations in one object has completely inconsistent performances for the two tasks. E.g. the features of salient locations are usually good for classification, while those around the object edge are good for regression. Inspired by this, we propose the Decoupling Head (DH) to disentangle the object classification and regression via the self-learned optimal feature extraction, which leads to a great improvement. Furthermore, we adjust the soft-NMS algorithm to adj-NMS to obtain stable performance improvement. Finally, a well-designed ensemble strategy via voting the bounding box location and confidence is proposed. We will also introduce several training/inferencing strategies and a bag of tricks that give minor improvement. Given those masses of details, we train and aggregate 28 global models with various backbones, heads and 3+2 expert models, and achieves the 1st place on the OpenImage 2019 Object Detection Challenge on the both public and private leadboards. Given such good instance bounding box, we further design a simple instance-level semantic segmentation pipeline and achieve the 1st place on the segmentation challenge.


page 2

page 5


Revisiting the Sibling Head in Object Detector

The “shared head for classification and localization” (sibling head), fi...

Towards Precise End-to-end Weakly Supervised Object Detection Network

It is challenging for weakly supervised object detection network to prec...

Team PFDet's Methods for Open Images Challenge 2019

We present the instance segmentation and the object detection method use...

Weakly Supervised Instance Segmentation by Deep Multi-Task Community Learning

We present an object segmentation algorithm based on community learning ...

Deep GrabCut for Object Selection

Most previous bounding-box-based segmentation methods assume the boundin...

2nd Place Solution in Google AI Open Images Object Detection Track 2019

We present an object detection framework based on PaddlePaddle. We put a...

1st Place Solutions for the UVO Challenge 2022

This paper describes the approach we have taken in the challenge. We sti...

Code Repositories


1st place models in Google OpenImage Detection Challenge 2019

view repo