# 1st Place Solution of LVIS Challenge 2020: A Good Box is not a Guarantee of a Good Mask

arXiv: https://arxiv.org/abs/2009.01559 · HTML: https://mlsanity.com/paper/2009.01559/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Sep 2020.

## Built on by (most cited first, 15 of 15)

- [EVA: Exploring the Limits of Masked Visual Representation Learning at Scale](https://mlsanity.com/paper/2211.07636/) (2022)
- [Detecting Twenty-thousand Classes using Image-level Supervision](https://mlsanity.com/paper/2201.02605/) (2022)
- [MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition](https://mlsanity.com/paper/2201.08383/) (2022)
- [Learning Open-World Object Proposals without Learning to Classify](https://mlsanity.com/paper/2108.06753/) (2021)
- [X-Paste: Revisiting Scalable Copy-Paste for Instance Segmentation using CLIP and StableDiffusion](https://mlsanity.com/paper/2212.03863/) (2022)
- [RefineMask: Towards High-Quality Instance Segmentation with Fine-Grained Features](https://mlsanity.com/paper/2104.08569/) (2021)
- [On Model Calibration for Long-Tailed Object Detection and Instance Segmentation](https://mlsanity.com/paper/2107.02170/) (2021)
- [MosaicFusion: Diffusion Models as Data Augmenters for Large Vocabulary Instance Segmentation](https://mlsanity.com/paper/2309.13042/) (2023)
- [MosaicOS: A Simple and Effective Use of Object-Centric Images for Long-Tailed Object Detection](https://mlsanity.com/paper/2102.08884/) (2021)
- [Proper Reuse of Image Classification Features Improves Object Detection](https://mlsanity.com/paper/2204.00484/) (2022)
- [DiverGen: Improving Instance Segmentation by Learning Wider Data Distribution with More Diverse Generative Data](https://mlsanity.com/paper/2405.10185/) (2024)
- [Zero-shot Object Detection Through Vision-Language Embedding Alignment](https://mlsanity.com/paper/2109.12066/) (2021)
- [The Equalization Losses: Gradient-Driven Training for Long-tailed Object Recognition](https://mlsanity.com/paper/2210.05566/) (2022)
- [Content-Augmented Feature Pyramid Network with Light Linear Spatial Transformers for Object Detection](https://mlsanity.com/paper/2105.09464/) (2021)
- [InstaDA: Augmenting Instance Segmentation Data with Dual-Agent System](https://mlsanity.com/paper/2509.02973/) (2025)

## Abstract (arXiv)

This article introduces the solutions of the team lvisTraveler for LVIS Challenge 2020. In this work, two characteristics of LVIS dataset are mainly considered: the long-tailed distribution and high quality instance segmentation mask. We adopt a two-stage training pipeline. In the first stage, we incorporate EQL and self-training to learn generalized representation. In the second stage, we utilize Balanced GroupSoftmax to promote the classifier, and propose a novel proposal assignment strategy and a new balanced mask loss for mask head to get more precise mask predictions. Finally, we achieve 41.5 and 41.2 AP on LVIS v1.0 val and test-dev splits respectively, outperforming the baseline based on X101-FPN-MaskRCNN by a large margin.