# BoxInst: High-Performance Instance Segmentation with Box Annotations

arXiv: https://arxiv.org/abs/2012.02310 · HTML: https://mlsanity.com/paper/2012.02310/

## Key facts

- Cited by 151 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Dec 2020.

## Built on by (most cited first, 30 of 151)

- [DanceTrack: Multi-Object Tracking in Uniform Appearance and Diverse Motion](https://mlsanity.com/paper/2111.14690/) (2021)
- [A Simple Framework for Open-Vocabulary Segmentation and Detection](https://mlsanity.com/paper/2303.08131/) (2023)
- [Universal Instance Perception as Object Discovery and Retrieval](https://mlsanity.com/paper/2303.06674/) (2023)
- [RSPrompter: Learning to Prompt for Remote Sensing Instance Segmentation based on Visual Foundation Model](https://mlsanity.com/paper/2306.16269/) (2023)
- [Transformer-Based Visual Segmentation: A Survey](https://mlsanity.com/paper/2304.09854/) (2023)
- [FreeSOLO: Learning to Segment Objects without Annotations](https://mlsanity.com/paper/2202.12181/) (2022)
- [MinVIS: A Minimal Video Instance Segmentation Framework without Video-based Training](https://mlsanity.com/paper/2208.02245/) (2022)
- [Open-Vocabulary Instance Segmentation via Robust Cross-Modal Pseudo-Labeling](https://mlsanity.com/paper/2111.12698/) (2021)
- [Pointly-Supervised Instance Segmentation](https://mlsanity.com/paper/2104.06404/) (2021)
- [Fine-Grained Egocentric Hand-Object Segmentation: Dataset, Model, and Applications](https://mlsanity.com/paper/2208.03826/) (2022)
- [GROUNDHOG: Grounding Large Language Models to Holistic Segmentation](https://mlsanity.com/paper/2402.16846/) (2024)
- [OneTracker: Unifying Visual Object Tracking with Foundation Models and Efficient Tuning](https://mlsanity.com/paper/2403.09634/) (2024)
- [DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervision](https://mlsanity.com/paper/2105.06464/) (2021)
- [Tree Energy Loss: Towards Sparsely Annotated Semantic Segmentation](https://mlsanity.com/paper/2203.10739/) (2022)
- [A Survey on Label-efficient Deep Image Segmentation: Bridging the Gap between Weak Supervision and Dense Prediction](https://mlsanity.com/paper/2207.01223/) (2022)
- [Box-supervised Instance Segmentation with Level Set Evolution](https://mlsanity.com/paper/2207.09055/) (2022)
- [H2RBox: Horizontal Box Annotation is All You Need for Oriented Object Detection](https://mlsanity.com/paper/2210.06742/) (2022)
- [Fully Convolutional Networks for Panoptic Segmentation with Point-based Supervision](https://mlsanity.com/paper/2108.07682/) (2021)
- [BoxTeacher: Exploring High-Quality Pseudo Labels for Weakly Supervised Instance Segmentation](https://mlsanity.com/paper/2210.05174/) (2022)
- [DaTaSeg: Taming a Universal Multi-Dataset Multi-Task Segmentation Model](https://mlsanity.com/paper/2306.01736/) (2023)
- [H2RBox-v2: Incorporating Symmetry for Boosting Horizontal Box Supervised Oriented Object Detection](https://mlsanity.com/paper/2304.04403/) (2023)
- [Semantic Image Segmentation: Two Decades of Research](https://mlsanity.com/paper/2302.06378/) (2023)
- [Beyond Semantic to Instance Segmentation: Weakly-Supervised Instance Segmentation via Semantic Knowledge Transfer and Self-Refinement](https://mlsanity.com/paper/2109.09477/) (2021)
- [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)
- [UniRef++: Segment Every Reference Object in Spatial and Temporal Spaces](https://mlsanity.com/paper/2312.15715/) (2023)
- [Noisy Boundaries: Lemon or Lemonade for Semi-supervised Instance Segmentation?](https://mlsanity.com/paper/2203.13427/) (2022)
- [Pointly-Supervised Panoptic Segmentation](https://mlsanity.com/paper/2210.13950/) (2022)
- [The Devil is in the Points: Weakly Semi-Supervised Instance Segmentation via Point-Guided Mask Representation](https://mlsanity.com/paper/2303.15062/) (2023)

## Abstract (arXiv)

We present a high-performance method that can achieve mask-level instance segmentation with only bounding-box annotations for training. While this setting has been studied in the literature, here we show significantly stronger performance with a simple design (e.g., dramatically improving previous best reported mask AP of 21.1% in Hsu et al. (2019) to 31.6% on the COCO dataset). Our core idea is to redesign the loss of learning masks in instance segmentation, with no modification to the segmentation network itself. The new loss functions can supervise the mask training without relying on mask annotations. This is made possible with two loss terms, namely, 1) a surrogate term that minimizes the discrepancy between the projections of the ground-truth box and the predicted mask; 2) a pairwise loss that can exploit the prior that proximal pixels with similar colors are very likely to have the same category label. Experiments demonstrate that the redesigned mask loss can yield surprisingly high-quality instance masks with only box annotations. For example, without using any mask annotations, with a ResNet-101 backbone and 3x training schedule, we achieve 33.2% mask AP on COCO test-dev split (vs. 39.1% of the fully supervised counterpart). Our excellent experiment results on COCO and Pascal VOC indicate that our method dramatically narrows the performance gap between weakly and fully supervised instance segmentation. Code is available at: https://git.io/AdelaiDet