# Iteratively Trained Interactive Segmentation

arXiv: https://arxiv.org/abs/1805.04398 · HTML: https://mlsanity.com/paper/1805.04398/

## Key facts

- Cited by 52 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 May 2018.

## Built on by (most cited first, 30 of 52)

- [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)
- [Segment Anything Model for Medical Image Analysis: an Experimental Study](https://mlsanity.com/paper/2304.10517/) (2023)
- [SegGPT: Segmenting Everything In Context](https://mlsanity.com/paper/2304.03284/) (2023)
- [Reviving Iterative Training with Mask Guidance for Interactive Segmentation](https://mlsanity.com/paper/2102.06583/) (2021)
- [FocalClick: Towards Practical Interactive Image Segmentation](https://mlsanity.com/paper/2204.02574/) (2022)
- [Caption Anything: Interactive Image Description with Diverse Multimodal Controls](https://mlsanity.com/paper/2305.02677/) (2023)
- [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)
- [AGILE3D: Attention Guided Interactive Multi-object 3D Segmentation](https://mlsanity.com/paper/2306.00977/) (2023)
- [Deep Interactive Segmentation of Medical Images: A Systematic Review and Taxonomy](https://mlsanity.com/paper/2311.13964/) (2023)
- [Interactive Object Segmentation in 3D Point Clouds](https://mlsanity.com/paper/2204.07183/) (2022)
- [A Simple Image Segmentation Framework via In-Context Examples](https://mlsanity.com/paper/2410.04842/) (2024)
- [CFR-ICL: Cascade-Forward Refinement with Iterative Click Loss for Interactive Image Segmentation](https://mlsanity.com/paper/2303.05620/) (2023)
- [Focused and Collaborative Feedback Integration for Interactive Image Segmentation](https://mlsanity.com/paper/2303.11880/) (2023)
- [Personal Fixations-Based Object Segmentation with Object Localization and Boundary Preservation](https://mlsanity.com/paper/2101.09014/) (2021)
- [DynaMITe: Dynamic Query Bootstrapping for Multi-object Interactive Segmentation Transformer](https://mlsanity.com/paper/2304.06668/) (2023)
- [Probabilistic Attention for Interactive Segmentation](https://mlsanity.com/paper/2106.15338/) (2021)
- [EISeg: An Efficient Interactive Segmentation Tool based on PaddlePaddle](https://mlsanity.com/paper/2210.08788/) (2022)
- [ScribbleSeg: Scribble-based Interactive Image Segmentation](https://mlsanity.com/paper/2303.11320/) (2023)
- [Adapting the Segment Anything Model During Usage in Novel Situations](https://mlsanity.com/paper/2404.08421/) (2024)
- [Interactive Class-Agnostic Object Counting](https://mlsanity.com/paper/2309.05277/) (2023)
- [UCP-Net: Unstructured Contour Points for Instance Segmentation](https://mlsanity.com/paper/2109.07592/) (2021)
- [Revisiting Click-based Interactive Video Object Segmentation](https://mlsanity.com/paper/2203.01784/) (2022)
- [Guiding the Guidance: A Comparative Analysis of User Guidance Signals for Interactive Segmentation of Volumetric Images](https://mlsanity.com/paper/2303.06942/) (2023)
- [Point-VOS: Pointing Up Video Object Segmentation](https://mlsanity.com/paper/2402.05917/) (2024)
- [Morphology-Aware Interactive Keypoint Estimation](https://mlsanity.com/paper/2209.07163/) (2022)
- [Interactive4D: Interactive 4D LiDAR Segmentation](https://mlsanity.com/paper/2410.08206/) (2024)
- [Interactive Object Segmentation with Dynamic Click Transform](https://mlsanity.com/paper/2106.10465/) (2021)
- [Generalizing Interactive Backpropagating Refinement for Dense Prediction](https://mlsanity.com/paper/2112.10969/) (2021)

## Abstract (arXiv)

Deep learning requires large amounts of training data to be effective. For the task of object segmentation, manually labeling data is very expensive, and hence interactive methods are needed. Following recent approaches, we develop an interactive object segmentation system which uses user input in the form of clicks as the input to a convolutional network. While previous methods use heuristic click sampling strategies to emulate user clicks during training, we propose a new iterative training strategy. During training, we iteratively add clicks based on the errors of the currently predicted segmentation. We show that our iterative training strategy together with additional improvements to the network architecture results in improved results over the state-of-the-art.