# A Fully Convolutional Two-Stream Fusion Network for Interactive Image Segmentation

arXiv: https://arxiv.org/abs/1807.02480 · HTML: https://mlsanity.com/paper/1807.02480/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Jul 2018.

## Built on by (most cited first, 15 of 15)

- [MIDeepSeg: Minimally Interactive Segmentation of Unseen Objects from Medical Images Using Deep Learning](https://mlsanity.com/paper/2104.12166/) (2021)
- [Personal Fixations-Based Object Segmentation with Object Localization and Boundary Preservation](https://mlsanity.com/paper/2101.09014/) (2021)
- [Boundary-aware Supervoxel-level Iteratively Refined Interactive 3D Image Segmentation with Multi-agent Reinforcement Learning](https://mlsanity.com/paper/2303.10692/) (2023)
- [Probabilistic Attention for Interactive Segmentation](https://mlsanity.com/paper/2106.15338/) (2021)
- [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)
- [Generalizing Interactive Backpropagating Refinement for Dense Prediction](https://mlsanity.com/paper/2112.10969/) (2021)
- [Interactive Segmentation for Diverse Gesture Types Without Context](https://mlsanity.com/paper/2307.10518/) (2023)
- [Feature Decoupling-Recycling Network for Fast Interactive Segmentation](https://mlsanity.com/paper/2308.03529/) (2023)
- [Exploring the Interactive Guidance for Unified and Effective Image Matting](https://mlsanity.com/paper/2205.08324/) (2022)
- [PE-MED: Prompt Enhancement for Interactive Medical Image Segmentation](https://mlsanity.com/paper/2308.13746/) (2023)
- [MST: Adaptive Multi-Scale Tokens Guided Interactive Segmentation](https://mlsanity.com/paper/2401.04403/) (2024)
- [Interactive Occlusion Boundary Estimation through Exploitation of Synthetic Data](https://mlsanity.com/paper/2408.15038/) (2024)
- [Hyper-Fusion Network for Semi-Automatic Segmentation of Skin Lesions](https://mlsanity.com/paper/2412.10816/) (2024)
- [RefCut: Interactive Segmentation with Reference Guidance](https://mlsanity.com/paper/2503.17820/) (2025)

## Abstract (arXiv)

In this paper, we propose a novel fully convolutional two-stream fusion network (FCTSFN) for interactive image segmentation. The proposed network includes two sub-networks: a two-stream late fusion network (TSLFN) that predicts the foreground at a reduced resolution, and a multi-scale refining network (MSRN) that refines the foreground at full resolution. The TSLFN includes two distinct deep streams followed by a fusion network. The intuition is that, since user interactions are more direct information on foreground/background than the image itself, the two-stream structure of the TSLFN reduces the number of layers between the pure user interaction features and the network output, allowing the user interactions to have a more direct impact on the segmentation result. The MSRN fuses the features from different layers of TSLFN with different scales, in order to seek the local to global information on the foreground to refine the segmentation result at full resolution. We conduct comprehensive experiments on four benchmark datasets. The results show that the proposed network achieves competitive performance compared to current state-of-the-art interactive image segmentation methods