Order-aware Interactive Segmentation
This work improves interactive segmentation for users needing precise object selection with minimal effort, representing a strong specific gain rather than a foundational change.
The paper tackles the problem of interactive segmentation by addressing the limited understanding of object order (relative depth) in scenes, proposing OIS which encodes order maps and uses order-aware attention to guide user clicks, resulting in state-of-the-art performance with improvements of 7.61 mIoU on HQSeg44K and 1.32 mIoU on DAVIS after one click, while doubling inference speed.
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