.png){kind=icon}
.png){kind=icon}
Return
Exemplar-guided interactive segmentation for multiple intra-class objects
.png){kind=icon}
OA
AI
DOI：10.1016/j.neucom.2026.133971.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Interactive image segmentation enables users to interact minimally with a machine, facilitating the gradual refinement of the segmentation mask for a target of interest. Previous studies have demonstrated impressive performance in extracting a single target mask through interactive segmentation. However, existing methods often overlook the information cues from previously interacted objects, despite real-world scenarios frequently involving multiple objects in the same category, leading to increased redundant user effort. To this end, we introduce a new interactive image segmentation framework for multiple objects in the same category within one image. Specifically, our model leverages Transformers to extract interaction-focused visual features from the image and the interactions to obtain a satisfactory mask of a target as an exemplar. For multiple objects, we propose an exemplar-informed module to enhance the learning of similarities among the objects of the target category. To combine attended features from different modules, we incorporate cross-attention blocks followed by a feature fusion module. Extensive experiments conducted on different datasets demonstrate that our model achieves superior performance compared to existing methods. Particularly, our model reduces users’ labor by around 15%, i.e., requiring two fewer clicks to achieve target IoUs 85% and 90% for multiple objects. Moreover, we conduct experiments in out-of-domain scenes (e.g., medical and remote sensing) to verify the effectiveness of the proposed model for various categories. These results further highlight our model’s potential as a flexible and practical annotation tool. The code will be released after publication.
Keywords:
Interactive image segmentation
Multiple objects
Annotation tool
Multimodal fusion
Human-computer interaction
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
6.5
Papers:
2.5W
Citations:
6.5W
Organization
No organization information available