# Deep Extreme Cut: From Extreme Points to Object Segmentation

arXiv: https://arxiv.org/abs/1711.09081 · HTML: https://mlsanity.com/paper/1711.09081/

## Key facts

- Cited by 127 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Nov 2017.

## Built on by (most cited first, 30 of 127)

- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Reviving Iterative Training with Mask Guidance for Interactive Segmentation](https://mlsanity.com/paper/2102.06583/) (2021)
- [Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion](https://mlsanity.com/paper/2103.07941/) (2021)
- [ReCo: Retrieve and Co-segment for Zero-shot Transfer](https://mlsanity.com/paper/2206.07045/) (2022)
- [SimpleClick: Interactive Image Segmentation with Simple Vision Transformers](https://mlsanity.com/paper/2210.11006/) (2022)
- [BigDatasetGAN: Synthesizing ImageNet with Pixel-wise Annotations](https://mlsanity.com/paper/2201.04684/) (2022)
- [One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation](https://mlsanity.com/paper/2104.02246/) (2021)
- [Pointly-Supervised Instance Segmentation](https://mlsanity.com/paper/2104.06404/) (2021)
- [Neural Volumetric Object Selection](https://mlsanity.com/paper/2205.14929/) (2022)
- [Unsupervised Semantic Segmentation with Self-supervised Object-centric Representations](https://mlsanity.com/paper/2207.05027/) (2022)
- [Mapping Degeneration Meets Label Evolution: Learning Infrared Small Target Detection with Single Point Supervision](https://mlsanity.com/paper/2304.01484/) (2023)
- [ScribblePrompt: Fast and Flexible Interactive Segmentation for Any Biomedical Image](https://mlsanity.com/paper/2312.07381/) (2023)
- [MIDeepSeg: Minimally Interactive Segmentation of Unseen Objects from Medical Images Using Deep Learning](https://mlsanity.com/paper/2104.12166/) (2021)
- [PseudoClick: Interactive Image Segmentation with Click Imitation](https://mlsanity.com/paper/2207.05282/) (2022)
- [EdgeFlow: Achieving Practical Interactive Segmentation with Edge-Guided Flow](https://mlsanity.com/paper/2109.09406/) (2021)
- [MONAI Label: A framework for AI-assisted Interactive Labeling of 3D Medical Images](https://mlsanity.com/paper/2203.12362/) (2022)
- [All you need are a few pixels: semantic segmentation with PixelPick](https://mlsanity.com/paper/2104.06394/) (2021)
- [Fully Convolutional Networks for Panoptic Segmentation with Point-based Supervision](https://mlsanity.com/paper/2108.07682/) (2021)
- [MODS -- A USV-oriented object detection and obstacle segmentation benchmark](https://mlsanity.com/paper/2105.02359/) (2021)
- [Deep Interactive Segmentation of Medical Images: A Systematic Review and Taxonomy](https://mlsanity.com/paper/2311.13964/) (2023)
- [UniVS: Unified and Universal Video Segmentation with Prompts as Queries](https://mlsanity.com/paper/2402.18115/) (2024)
- [Weakly-Supervised Salient Object Detection Using Point Supervision](https://mlsanity.com/paper/2203.11652/) (2022)
- [A Spacecraft Dataset for Detection, Segmentation and Parts Recognition](https://mlsanity.com/paper/2106.08186/) (2021)
- [From colouring-in to pointillism: revisiting semantic segmentation supervision](https://mlsanity.com/paper/2210.14142/) (2022)
- [Target-Aware Object Discovery and Association for Unsupervised Video Multi-Object Segmentation](https://mlsanity.com/paper/2104.04782/) (2021)
- [Inter Extreme Points Geodesics for End-to-End Weakly Supervised Image Segmentation](https://mlsanity.com/paper/2107.00583/) (2021)
- [Pointly-Supervised Panoptic Segmentation](https://mlsanity.com/paper/2210.13950/) (2022)
- [InterFormer: Real-time Interactive Image Segmentation](https://mlsanity.com/paper/2304.02942/) (2023)
- [Monte Carlo Linear Clustering with Single-Point Supervision is Enough for Infrared Small Target Detection](https://mlsanity.com/paper/2304.04442/) (2023)
- [Focused and Collaborative Feedback Integration for Interactive Image Segmentation](https://mlsanity.com/paper/2303.11880/) (2023)

## Abstract (arXiv)

This paper explores the use of extreme points in an object (left-most, right-most, top, bottom pixels) as input to obtain precise object segmentation for images and videos. We do so by adding an extra channel to the image in the input of a convolutional neural network (CNN), which contains a Gaussian centered in each of the extreme points. The CNN learns to transform this information into a segmentation of an object that matches those extreme points. We demonstrate the usefulness of this approach for guided segmentation (grabcut-style), interactive segmentation, video object segmentation, and dense segmentation annotation. We show that we obtain the most precise results to date, also with less user input, in an extensive and varied selection of benchmarks and datasets. All our models and code are publicly available on http://www.vision.ee.ethz.ch/~cvlsegmentation/dextr/.