# Getting to 99% Accuracy in Interactive Segmentation

arXiv: https://arxiv.org/abs/2003.07932 · HTML: https://mlsanity.com/paper/2003.07932/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Mar 2020.

## Built on by (most cited first, 19 of 19)

- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Medical SAM Adapter: Adapting Segment Anything Model for Medical Image Segmentation](https://mlsanity.com/paper/2304.12620/) (2023)
- [FocalClick: Towards Practical Interactive Image Segmentation](https://mlsanity.com/paper/2204.02574/) (2022)
- [ScribblePrompt: Fast and Flexible Interactive Segmentation for Any Biomedical Image](https://mlsanity.com/paper/2312.07381/) (2023)
- [EdgeSAM: Prompt-In-the-Loop Distillation for SAM](https://mlsanity.com/paper/2312.06660/) (2023)
- [InterFormer: Real-time Interactive Image Segmentation](https://mlsanity.com/paper/2304.02942/) (2023)
- [Interactive Segmentation as Gaussian Process Classification](https://mlsanity.com/paper/2302.14578/) (2023)
- [AdaptiveClick: Clicks-aware Transformer with Adaptive Focal Loss for Interactive Image Segmentation](https://mlsanity.com/paper/2305.04276/) (2023)
- [UCP-Net: Unstructured Contour Points for Instance Segmentation](https://mlsanity.com/paper/2109.07592/) (2021)
- [MFP: Making Full Use of Probability Maps for Interactive Image Segmentation](https://mlsanity.com/paper/2404.18448/) (2024)
- [SAM-PD: How Far Can SAM Take Us in Tracking and Segmenting Anything in Videos by Prompt Denoising](https://mlsanity.com/paper/2403.04194/) (2024)
- [Strike the Balance: On-the-Fly Uncertainty based User Interactions for Long-Term Video Object Segmentation](https://mlsanity.com/paper/2408.00169/) (2024)
- [Interactive Object Segmentation with Dynamic Click Transform](https://mlsanity.com/paper/2106.10465/) (2021)
- [Interactive Segmentation for Diverse Gesture Types Without Context](https://mlsanity.com/paper/2307.10518/) (2023)
- [DC-TTA: Divide-and-Conquer Framework for Test-Time Adaptation of Interactive Segmentation](https://mlsanity.com/paper/2506.23104/) (2025)
- [PVPUFormer: Probabilistic Visual Prompt Unified Transformer for Interactive Image Segmentation](https://mlsanity.com/paper/2306.06656/) (2023)
- [SonoSAMTrack -- Segment and Track Anything on Ultrasound Images](https://mlsanity.com/paper/2310.16872/) (2023)
- [ClickAttention: Click Region Similarity Guided Interactive Segmentation](https://mlsanity.com/paper/2408.06021/) (2024)
- [FocalClick-XL: Towards Unified and High-quality Interactive Segmentation](https://mlsanity.com/paper/2506.14686/) (2025)

## Abstract (arXiv)

Interactive object cutout tools are the cornerstone of the image editing workflow. Recent deep-learning based interactive segmentation algorithms have made significant progress in handling complex images and rough binary selections can typically be obtained with just a few clicks. Yet, deep learning techniques tend to plateau once this rough selection has been reached. In this work, we interpret this plateau as the inability of current algorithms to sufficiently leverage each user interaction and also as the limitations of current training/testing datasets. We propose a novel interactive architecture and a novel training scheme that are both tailored to better exploit the user workflow. We also show that significant improvements can be further gained by introducing a synthetic training dataset that is specifically designed for complex object boundaries. Comprehensive experiments support our approach, and our network achieves state of the art performance.