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

Abstract

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 \cite{ren2015faster} 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. \textit{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.

References in corpus (6)

• MMDetection: Open MMLab Detection Toolbox and Benchmark
• The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale
• Rethinking Classification and Localization for Object Detection
• Solution for Large-Scale Hierarchical Object Detection Datasets with Incomplete Annotation and Data Imbalance
• PFDet: 2nd Place Solution to Open Images Challenge 2018 Object Detection Track
• Detecting 11K Classes: Large Scale Object Detection without Fine-Grained Bounding Boxes

Cited by in corpus (5)

• 1st Place Solution of LVIS Challenge 2020: A Good Box is not a Guarantee of a Good Mask
• Adaptive Label Smoothing
• 2nd Place Solution for Waymo Open Dataset Challenge -- 2D Object Detection
• 1st Place Solution for YouTubeVOS Challenge 2021:Video Instance Segmentation
• Probabilistic Ranking-Aware Ensembles for Enhanced Object Detections