# Box-supervised Instance Segmentation with Level Set Evolution

arXiv: https://arxiv.org/abs/2207.09055 · HTML: https://mlsanity.com/paper/2207.09055/

## Key facts

- Cited by 41 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 55 references that are in the map.
- First posted on arXiv 19 Jul 2022.

## Builds on (most cited first, 30 of 30)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/1606.04797/) (2016)
- [MMDetection: Open MMLab Detection Toolbox and Benchmark](https://mlsanity.com/paper/1906.07155/) (2019)
- [The Liver Tumor Segmentation Benchmark (LiTS)](https://mlsanity.com/paper/1901.04056/) (2019)
- [YOLACT: Real-time Instance Segmentation](https://mlsanity.com/paper/1904.02689/) (2019)
- [PointRend: Image Segmentation as Rendering](https://mlsanity.com/paper/1912.08193/) (2019)
- [Deep Layer Aggregation](https://mlsanity.com/paper/1707.06484/) (2017)
- [Conditional Convolutions for Instance Segmentation](https://mlsanity.com/paper/2003.05664/) (2020)
- [Mask Scoring R-CNN](https://mlsanity.com/paper/1903.00241/) (2019)
- [Simple Does It: Weakly Supervised Instance and Semantic Segmentation](https://mlsanity.com/paper/1603.07485/) (2016)
- [iSAID: A Large-scale Dataset for Instance Segmentation in Aerial Images](https://mlsanity.com/paper/1905.12886/) (2019)
- [PolarMask: Single Shot Instance Segmentation with Polar Representation](https://mlsanity.com/paper/1909.13226/) (2019)
- [BoxInst: High-Performance Instance Segmentation with Box Annotations](https://mlsanity.com/paper/2012.02310/) (2020)
- [Deep Snake for Real-Time Instance Segmentation](https://mlsanity.com/paper/2001.01629/) (2020)
- [BBAM: Bounding Box Attribution Map for Weakly Supervised Semantic and Instance Segmentation](https://mlsanity.com/paper/2103.08907/) (2021)
- [Multiscale Combinatorial Grouping for Image Segmentation and Object Proposal Generation](https://mlsanity.com/paper/1503.00848/) (2015)
- [YOLACT++: Better Real-time Instance Segmentation](https://mlsanity.com/paper/1912.06218/) (2019)
- [Boundary-preserving Mask R-CNN](https://mlsanity.com/paper/2007.08921/) (2020)
- [DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervision](https://mlsanity.com/paper/2105.06464/) (2021)
- [RefineMask: Towards High-Quality Instance Segmentation with Fine-Grained Features](https://mlsanity.com/paper/2104.08569/) (2021)
- [Tree Energy Loss: Towards Sparsely Annotated Semantic Segmentation](https://mlsanity.com/paper/2203.10739/) (2022)
- [Mumford-Shah Loss Functional for Image Segmentation with Deep Learning](https://mlsanity.com/paper/1904.02872/) (2019)
- [Weakly Supervised Instance Segmentation by Learning Annotation Consistent Instances](https://mlsanity.com/paper/2007.09397/) (2020)
- [Learnable Tree Filter for Structure-preserving Feature Transform](https://mlsanity.com/paper/1909.12513/) (2019)
- [Weakly-supervised Instance Segmentation via Class-agnostic Learning with Salient Images](https://mlsanity.com/paper/2104.01526/) (2021)
- [LevelSet R-CNN: A Deep Variational Method for Instance Segmentation](https://mlsanity.com/paper/2007.15629/) (2020)
- [Deep Variational Instance Segmentation](https://mlsanity.com/paper/2007.11576/) (2020)
- [Weakly Supervised Instance Segmentation Using Hybrid Network](https://mlsanity.com/paper/1812.04831/) (2018)

## Built on by (most cited first, 30 of 41)

- [A Simple Framework for Open-Vocabulary Segmentation and Detection](https://mlsanity.com/paper/2303.08131/) (2023)
- [H2RBox: Horizontal Box Annotation is All You Need for Oriented Object Detection](https://mlsanity.com/paper/2210.06742/) (2022)
- [BoxTeacher: Exploring High-Quality Pseudo Labels for Weakly Supervised Instance Segmentation](https://mlsanity.com/paper/2210.05174/) (2022)
- [H2RBox-v2: Incorporating Symmetry for Boosting Horizontal Box Supervised Oriented Object Detection](https://mlsanity.com/paper/2304.04403/) (2023)
- [PointOBB: Learning Oriented Object Detection via Single Point Supervision](https://mlsanity.com/paper/2311.14757/) (2023)
- [Point2Mask: Point-supervised Panoptic Segmentation via Optimal Transport](https://mlsanity.com/paper/2308.01779/) (2023)
- [Box2Mask: Box-supervised Instance Segmentation via Level-set Evolution](https://mlsanity.com/paper/2212.01579/) (2022)
- [The Devil is in the Points: Weakly Semi-Supervised Instance Segmentation via Point-Guided Mask Representation](https://mlsanity.com/paper/2303.15062/) (2023)
- [Mask-Free Video Instance Segmentation](https://mlsanity.com/paper/2303.15904/) (2023)
- [U3DS3: Unsupervised 3D Semantic Scene Segmentation](https://mlsanity.com/paper/2311.06018/) (2023)
- [Semantic-aware SAM for Point-Prompted Instance Segmentation](https://mlsanity.com/paper/2312.15895/) (2023)
- [Vision Transformers Are Good Mask Auto-Labelers](https://mlsanity.com/paper/2301.03992/) (2023)
- [BoxSnake: Polygonal Instance Segmentation with Box Supervision](https://mlsanity.com/paper/2303.11630/) (2023)
- [SIM: Semantic-aware Instance Mask Generation for Box-Supervised Instance Segmentation](https://mlsanity.com/paper/2303.08578/) (2023)
- [WeakSAM: Segment Anything Meets Weakly-supervised Instance-level Recognition](https://mlsanity.com/paper/2402.14812/) (2024)
- [Label-efficient Semantic Scene Completion with Scribble Annotations](https://mlsanity.com/paper/2405.15170/) (2024)
- [PointOBB-v3: Expanding Performance Boundaries of Single Point-Supervised Oriented Object Detection](https://mlsanity.com/paper/2501.13898/) (2025)
- [Label-efficient Segmentation via Affinity Propagation](https://mlsanity.com/paper/2310.10533/) (2023)
- [GaPro: Box-Supervised 3D Point Cloud Instance Segmentation Using Gaussian Processes as Pseudo Labelers](https://mlsanity.com/paper/2307.13251/) (2023)
- [Wholly-WOOD: Wholly Leveraging Diversified-quality Labels for Weakly-supervised Oriented Object Detection](https://mlsanity.com/paper/2502.09471/) (2025)
- [LMMs Meet Object-Centric Vision: Understanding, Segmentation, Editing and Generation](https://mlsanity.com/paper/2604.11789/) (2026)
- [Fine-grained Background Representation for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2406.15755/) (2024)
- [AsyInst: Asymmetric Affinity with DepthGrad and Color for Box-Supervised Instance Segmentation](https://mlsanity.com/paper/2212.03517/) (2022)
- [Extreme Point Supervised Instance Segmentation](https://mlsanity.com/paper/2405.20729/) (2024)
- [Flip Learning: Weakly Supervised Erase to Segment Nodules in Breast Ultrasound](https://mlsanity.com/paper/2503.20685/) (2025)
- [Partial Weakly-Supervised Oriented Object Detection](https://mlsanity.com/paper/2507.02751/) (2025)
- [Advancing Visual Large Language Model for Multi-granular Versatile Perception](https://mlsanity.com/paper/2507.16213/) (2025)
- [IBoxCLA: Towards Robust Box-supervised Segmentation of Polyp via Improved Box-dice and Contrastive Latent-anchors](https://mlsanity.com/paper/2310.07248/) (2023)
- [Boosting Box-supervised Instance Segmentation with Pseudo Depth](https://mlsanity.com/paper/2403.01214/) (2024)
- [PWISeg: Point-based Weakly-supervised Instance Segmentation for Surgical Instruments](https://mlsanity.com/paper/2311.09819/) (2023)

## Abstract (arXiv)

In contrast to the fully supervised methods using pixel-wise mask labels, box-supervised instance segmentation takes advantage of the simple box annotations, which has recently attracted a lot of research attentions. In this paper, we propose a novel single-shot box-supervised instance segmentation approach, which integrates the classical level set model with deep neural network delicately. Specifically, our proposed method iteratively learns a series of level sets through a continuous Chan-Vese energy-based function in an end-to-end fashion. A simple mask supervised SOLOv2 model is adapted to predict the instance-aware mask map as the level set for each instance. Both the input image and its deep features are employed as the input data to evolve the level set curves, where a box projection function is employed to obtain the initial boundary. By minimizing the fully differentiable energy function, the level set for each instance is iteratively optimized within its corresponding bounding box annotation. The experimental results on four challenging benchmarks demonstrate the leading performance of our proposed approach to robust instance segmentation in various scenarios. The code is available at: https://github.com/LiWentomng/boxlevelset.