# Continuous Adaptation for Interactive Object Segmentation by Learning from Corrections

arXiv: https://arxiv.org/abs/1911.12709 · HTML: https://mlsanity.com/paper/1911.12709/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Nov 2019.

## Built on by (most cited first, 30 of 36)

- [Reviving Iterative Training with Mask Guidance for Interactive Segmentation](https://mlsanity.com/paper/2102.06583/) (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)
- [AGILE3D: Attention Guided Interactive Multi-object 3D Segmentation](https://mlsanity.com/paper/2306.00977/) (2023)
- [Interactive Object Segmentation in 3D Point Clouds](https://mlsanity.com/paper/2204.07183/) (2022)
- [DIAL: Deep Interactive and Active Learning for Semantic Segmentation in Remote Sensing](https://mlsanity.com/paper/2201.01047/) (2022)
- [Focused and Collaborative Feedback Integration for Interactive Image Segmentation](https://mlsanity.com/paper/2303.11880/) (2023)
- [Interactive Segmentation as Gaussian Process Classification](https://mlsanity.com/paper/2302.14578/) (2023)
- [DynaMITe: Dynamic Query Bootstrapping for Multi-object Interactive Segmentation Transformer](https://mlsanity.com/paper/2304.06668/) (2023)
- [Boundary-aware Supervoxel-level Iteratively Refined Interactive 3D Image Segmentation with Multi-agent Reinforcement Learning](https://mlsanity.com/paper/2303.10692/) (2023)
- [MultiverSeg: Scalable Interactive Segmentation of Biomedical Imaging Datasets with In-Context Guidance](https://mlsanity.com/paper/2412.15058/) (2024)
- [Probabilistic Attention for Interactive Segmentation](https://mlsanity.com/paper/2106.15338/) (2021)
- [Neural Interactive Keypoint Detection](https://mlsanity.com/paper/2308.10174/) (2023)
- [AdaptiveClick: Clicks-aware Transformer with Adaptive Focal Loss for Interactive Image Segmentation](https://mlsanity.com/paper/2305.04276/) (2023)
- [EISeg: An Efficient Interactive Segmentation Tool based on PaddlePaddle](https://mlsanity.com/paper/2210.08788/) (2022)
- [Multi-granularity Interaction Simulation for Unsupervised Interactive Segmentation](https://mlsanity.com/paper/2303.13399/) (2023)
- [Adapting the Segment Anything Model During Usage in Novel Situations](https://mlsanity.com/paper/2404.08421/) (2024)
- [VideoClick: Video Object Segmentation with a Single Click](https://mlsanity.com/paper/2101.06545/) (2021)
- [Revisiting Click-based Interactive Video Object Segmentation](https://mlsanity.com/paper/2203.01784/) (2022)
- [You Point, I Learn: Online Adaptation of Interactive Segmentation Models for Handling Distribution Shifts in Medical Imaging](https://mlsanity.com/paper/2503.06717/) (2025)
- [Strike the Balance: On-the-Fly Uncertainty based User Interactions for Long-Term Video Object Segmentation](https://mlsanity.com/paper/2408.00169/) (2024)
- [Interactive4D: Interactive 4D LiDAR Segmentation](https://mlsanity.com/paper/2410.08206/) (2024)
- [Human-in-the-Loop Local Corrections of 3D Scene Layouts via Infilling](https://mlsanity.com/paper/2503.11806/) (2025)
- [Contour-based Interactive Segmentation](https://mlsanity.com/paper/2302.06353/) (2023)
- [Refining Segmentation On-the-Fly: An Interactive Framework for Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2403.06401/) (2024)
- [DC-TTA: Divide-and-Conquer Framework for Test-Time Adaptation of Interactive Segmentation](https://mlsanity.com/paper/2506.23104/) (2025)
- [Rethinking Interactive Image Segmentation: Feature Space Annotation](https://mlsanity.com/paper/2101.04378/) (2021)
- [RAIS: Robust and Accurate Interactive Segmentation via Continual Learning](https://mlsanity.com/paper/2210.10984/) (2022)
- [Probabilistic Interactive 3D Segmentation with Hierarchical Neural Processes](https://mlsanity.com/paper/2505.01726/) (2025)
- [RootPainter3D: Interactive-machine-learning enables rapid and accurate contouring for radiotherapy](https://mlsanity.com/paper/2106.11942/) (2021)

## Abstract (arXiv)

In interactive object segmentation a user collaborates with a computer vision model to segment an object. Recent works employ convolutional neural networks for this task: Given an image and a set of corrections made by the user as input, they output a segmentation mask. These approaches achieve strong performance by training on large datasets but they keep the model parameters unchanged at test time. Instead, we recognize that user corrections can serve as sparse training examples and we propose a method that capitalizes on that idea to update the model parameters on-the-fly to the data at hand. Our approach enables the adaptation to a particular object and its background, to distributions shifts in a test set, to specific object classes, and even to large domain changes, where the imaging modality changes between training and testing. We perform extensive experiments on 8 diverse datasets and show: Compared to a model with frozen parameters, our method reduces the required corrections (i) by 9%-30% when distribution shifts are small between training and testing; (ii) by 12%-44% when specializing to a specific class; (iii) and by 60% and 77% when we completely change domain between training and testing.