Interactive segmentation aims to accurately segment target objects with minimal user interactions. However, current methods often fail to accurately separate target objects from the background, due to a limited understanding of order, the relative depth between objects in a scene. To address this issue, we propose OIS: order-aware interactive segmentation, where we explicitly encode the relative depth between objects into order maps. We introduce a novel order-aware attention, where the order maps seamlessly guide the user interactions (in the form of clicks) to attend to the image features. We further present an object-aware attention module to incorporate a strong object-level understanding to better differentiate objects with similar order. Our approach allows both dense and sparse integration of user clicks, enhancing both accuracy and efficiency as compared to prior works. Experimental results demonstrate that OIS achieves state-of-the-art performance, improving mIoU after one click by 7.61 on the HQSeg44K dataset and 1.32 on the DAVIS dataset as compared to the previous state-of-the-art SegNext, while also doubling inference speed compared to current leading methods. The project page is https://ukaukaaaa.github.io/projects/OIS/index.html
@article{arxiv.2410.12214,
title = {Order-aware Interactive Segmentation},
author = {Bin Wang and Anwesa Choudhuri and Meng Zheng and Zhongpai Gao and Benjamin Planche and Andong Deng and Qin Liu and Terrence Chen and Ulas Bagci and Ziyan Wu},
journal= {arXiv preprint arXiv:2410.12214},
year = {2025}
}
Comments
Accepted by ICLR 2025 Interactive demo can be found in project page: https://ukaukaaaa.github.io/projects/OIS/index.html