# LVIS Challenge Track Technical Report 1st Place Solution: Distribution Balanced and Boundary Refinement for Large Vocabulary Instance Segmentation

arXiv: https://arxiv.org/abs/2111.02668 · HTML: https://mlsanity.com/paper/2111.02668/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 12 references that are in the map.
- First posted on arXiv 4 Nov 2021.

## Builds on (most cited first, 12 of 12)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [YOLOv4: Optimal Speed and Accuracy of Object Detection](https://mlsanity.com/paper/2004.10934/) (2020)
- [LVIS: A Dataset for Large Vocabulary Instance Segmentation](https://mlsanity.com/paper/1908.03195/) (2019)
- [Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation](https://mlsanity.com/paper/2012.07177/) (2020)
- [Hybrid Task Cascade for Instance Segmentation](https://mlsanity.com/paper/1901.07518/) (2019)
- [Mask Scoring R-CNN](https://mlsanity.com/paper/1903.00241/) (2019)
- [Boundary IoU: Improving Object-Centric Image Segmentation Evaluation](https://mlsanity.com/paper/2103.16562/) (2021)
- [Seesaw Loss for Long-Tailed Instance Segmentation](https://mlsanity.com/paper/2008.10032/) (2020)
- [CBNet: A Composite Backbone Network Architecture for Object Detection](https://mlsanity.com/paper/2107.00420/) (2021)
- [Evaluating Large-Vocabulary Object Detectors: The Devil is in the Details](https://mlsanity.com/paper/2102.01066/) (2021)
- [RefineMask: Towards High-Quality Instance Segmentation with Fine-Grained Features](https://mlsanity.com/paper/2104.08569/) (2021)

## Built on by (most cited first, 5 of 5)

- [Exploring Plain Vision Transformer Backbones for Object Detection](https://mlsanity.com/paper/2203.16527/) (2022)
- [EVA: Exploring the Limits of Masked Visual Representation Learning at Scale](https://mlsanity.com/paper/2211.07636/) (2022)
- [The effectiveness of MAE pre-pretraining for billion-scale pretraining](https://mlsanity.com/paper/2303.13496/) (2023)
- [Window Attention is Bugged: How not to Interpolate Position Embeddings](https://mlsanity.com/paper/2311.05613/) (2023)
- [PET-DINO: Unifying Visual Cues into Grounding DINO with Prompt-Enriched Training](https://mlsanity.com/paper/2604.00503/) (2026)

## Abstract (arXiv)

This report introduces the technical details of the team FuXi-Fresher for LVIS Challenge 2021. Our method focuses on the problem in following two aspects: the long-tail distribution and the segmentation quality of mask and boundary. Based on the advanced HTC instance segmentation algorithm, we connect transformer backbone(Swin-L) through composite connections inspired by CBNetv2 to enhance the baseline results. To alleviate the problem of long-tail distribution, we design a Distribution Balanced method which includes dataset balanced and loss function balaced modules. Further, we use a Mask and Boundary Refinement method composed with mask scoring and refine-mask algorithms to improve the segmentation quality. In addition, we are pleasantly surprised to find that early stopping combined with EMA method can achieve a great improvement. Finally, by using multi-scale testing and increasing the upper limit of the number of objects detected per image, we achieved more than 45.4% boundary AP on the val set of LVIS Challenge 2021. On the test data of LVIS Challenge 2021, we rank 1st and achieve 48.1% AP. Notably, our APr 47.5% is very closed to the APf 48.0%.