ClickAttention: Click Region Similarity Guided Interactive Segmentation
This work addresses the need for more efficient and accurate interactive segmentation tools for users in computer vision, though it is incremental as it builds on existing click-based methods.
The paper tackles the problem of interactive segmentation requiring too many clicks and poor efficiency by proposing a click attention algorithm that expands positive click influence and a discriminative affinity loss to reduce interference, achieving state-of-the-art performance with fewer parameters.
Interactive segmentation algorithms based on click points have garnered significant attention from researchers in recent years. However, existing studies typically use sparse click maps as model inputs to segment specific target objects, which primarily affect local regions and have limited abilities to focus on the whole target object, leading to increased times of clicks. In addition, most existing algorithms can not balance well between high performance and efficiency. To address this issue, we propose a click attention algorithm that expands the influence range of positive clicks based on the similarity between positively-clicked regions and the whole input. We also propose a discriminative affinity loss to reduce the attention coupling between positive and negative click regions to avoid an accuracy decrease caused by mutual interference between positive and negative clicks. Extensive experiments demonstrate that our approach is superior to existing methods and achieves cutting-edge performance in fewer parameters. An interactive demo and all reproducible codes will be released at https://github.com/hahamyt/ClickAttention.