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

arXiv: https://arxiv.org/abs/2003.07557 · HTML: https://mlsanity.com/paper/2003.07557/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Mar 2020.

## Built on by (most cited first, 10 of 10)

- [InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions](https://mlsanity.com/paper/2211.05778/) (2022)
- [Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipe](https://mlsanity.com/paper/2209.05324/) (2022)
- [CBNet: A Composite Backbone Network Architecture for Object Detection](https://mlsanity.com/paper/2107.00420/) (2021)
- [Look Closer to Segment Better: Boundary Patch Refinement for Instance Segmentation](https://mlsanity.com/paper/2104.05239/) (2021)
- [1st Place Solution for YouTubeVOS Challenge 2021:Video Instance Segmentation](https://mlsanity.com/paper/2106.06649/) (2021)
- [Fractal Calibration for long-tailed object detection](https://mlsanity.com/paper/2410.11774/) (2024)
- [Probabilistic Ranking-Aware Ensembles for Enhanced Object Detections](https://mlsanity.com/paper/2105.03139/) (2021)
- [Improving Domain Generalization by Learning without Forgetting: Application in Retail Checkout](https://mlsanity.com/paper/2207.05422/) (2022)
- [Statistical Foundation Behind Machine Learning and Its Impact on Computer Vision](https://mlsanity.com/paper/2209.02691/) (2022)
- [Towards Establishing Systematic Classification Requirements for Automated Driving](https://mlsanity.com/paper/2307.14058/) (2023)

## Abstract (arXiv)

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 citeren2015faster 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. textitE.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.