# MonoBox: Tightness-free Box-supervised Polyp Segmentation using Monotonicity Constraint

arXiv: https://arxiv.org/abs/2404.01188 · HTML: https://mlsanity.com/paper/2404.01188/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 48 references that are in the map.
- First posted on arXiv 1 Apr 2024.

## Builds on (most cited first, 28 of 28)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels](https://mlsanity.com/paper/1804.06872/) (2018)
- [MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels](https://mlsanity.com/paper/1712.05055/) (2017)
- [Kvasir-SEG: A Segmented Polyp Dataset](https://mlsanity.com/paper/1911.07069/) (2019)
- [Symmetric Cross Entropy for Robust Learning with Noisy Labels](https://mlsanity.com/paper/1908.06112/) (2019)
- [PraNet: Parallel Reverse Attention Network for Polyp Segmentation](https://mlsanity.com/paper/2006.11392/) (2020)
- [Robust Loss Functions under Label Noise for Deep Neural Networks](https://mlsanity.com/paper/1712.09482/) (2017)
- [Normalized Loss Functions for Deep Learning with Noisy Labels](https://mlsanity.com/paper/2006.13554/) (2020)
- [Weakly Supervised Learning of Instance Segmentation with Inter-pixel Relations](https://mlsanity.com/paper/1904.05044/) (2019)
- [BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1503.01640/) (2015)
- [A Benchmark for Endoluminal Scene Segmentation of Colonoscopy Images](https://mlsanity.com/paper/1612.00799/) (2016)
- [Dimensionality-Driven Learning with Noisy Labels](https://mlsanity.com/paper/1806.02612/) (2018)
- [Polyp-PVT: Polyp Segmentation with Pyramid Vision Transformers](https://mlsanity.com/paper/2108.06932/) (2021)
- [BoxInst: High-Performance Instance Segmentation with Box Annotations](https://mlsanity.com/paper/2012.02310/) (2020)
- [Bounding Box Regression with Uncertainty for Accurate Object Detection](https://mlsanity.com/paper/1809.08545/) (2018)
- [Shallow Attention Network for Polyp Segmentation](https://mlsanity.com/paper/2108.00882/) (2021)
- [Pointly-Supervised Instance Segmentation](https://mlsanity.com/paper/2104.06404/) (2021)
- [Automatic Polyp Segmentation via Multi-scale Subtraction Network](https://mlsanity.com/paper/2108.05082/) (2021)
- [Background-Aware Pooling and Noise-Aware Loss for Weakly-Supervised Semantic Segmentation](https://mlsanity.com/paper/2104.00905/) (2021)
- [BoxTeacher: Exploring High-Quality Pseudo Labels for Weakly Supervised Instance Segmentation](https://mlsanity.com/paper/2210.05174/) (2022)
- [WeakPolyp: You Only Look Bounding Box for Polyp Segmentation](https://mlsanity.com/paper/2307.10912/) (2023)
- [Bounding Box Tightness Prior for Weakly Supervised Image Segmentation](https://mlsanity.com/paper/2110.00934/) (2021)
- [Vision Transformers Are Good Mask Auto-Labelers](https://mlsanity.com/paper/2301.03992/) (2023)
- [Spatial Self-Distillation for Object Detection with Inaccurate Bounding Boxes](https://mlsanity.com/paper/2307.12101/) (2023)
- [BoxShrink: From Bounding Boxes to Segmentation Masks](https://mlsanity.com/paper/2208.03142/) (2022)
- [IBoxCLA: Towards Robust Box-supervised Segmentation of Polyp via Improved Box-dice and Contrastive Latent-anchors](https://mlsanity.com/paper/2310.07248/) (2023)
- [Polar Transformation Based Multiple Instance Learning Assisting Weakly Supervised Image Segmentation With Loose Bounding Box Annotations](https://mlsanity.com/paper/2203.06000/) (2022)

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

- [Holistic White-light Polyp Classification via Alignment-free Dense Distillation of Auxiliary Optical Chromoendoscopy](https://mlsanity.com/paper/2505.19319/) (2025)
- [First-frame Supervised Video Polyp Segmentation via Propagative and Semantic Dual-teacher Network](https://mlsanity.com/paper/2412.16503/) (2024)
- [Moving Light Adaptive Colonoscopy Reconstruction via Illumination-Attenuation-Aware 3D Gaussian Splatting](https://mlsanity.com/paper/2510.18739/) (2025)
- [Brain-Adapter: A Dual-Stream Vision-Language MIL Framework for Comprehensive 3D CT Diagnosis of Acute Intracranial Pathologies](https://mlsanity.com/paper/2606.23494/) (2026)
- [EndoVLM: An Endoscopy Vision-Language Pre-training Model via Anatomy-Guided Sparsity and Progressive Alignment](https://mlsanity.com/paper/2608.04472/) (2026)

## Abstract (arXiv)

We propose MonoBox, an innovative box-supervised segmentation method constrained by monotonicity to liberate its training from the user-unfriendly box-tightness assumption. In contrast to conventional box-supervised segmentation, where the box edges must precisely touch the target boundaries, MonoBox leverages imprecisely-annotated boxes to achieve robust pixel-wise segmentation. The 'linchpin' is that, within the noisy zones around box edges, MonoBox discards the traditional misguiding multiple-instance learning loss, and instead optimizes a carefully-designed objective, termed monotonicity constraint. Along directions transitioning from the foreground to background, this new constraint steers responses to adhere to a trend of monotonically decreasing values. Consequently, the originally unreliable learning within the noisy zones is transformed into a correct and effective monotonicity optimization. Moreover, an adaptive label correction is introduced, enabling MonoBox to enhance the tightness of box annotations using predicted masks from the previous epoch and dynamically shrink the noisy zones as training progresses. We verify MonoBox in the box-supervised segmentation task of polyps, where satisfying box-tightness is challenging due to the vague boundaries between the polyp and normal tissues. Experiments on both public synthetic and in-house real noisy datasets demonstrate that MonoBox exceeds other anti-noise state-of-the-arts by improving Dice by at least 5.5% and 3.3%, respectively. Codes are at https://github.com/Huster-Hq/MonoBox.