Structured Click Control in Transformer-based Interactive Segmentation

arXiv:2405.04009v1 Announce Type: new
Abstract: Click-point-based interactive segmentation has received widespread attention due to its efficiency. However, it's hard for existing algorithms to obtain precise and robust responses after multiple clicks. In this case, the segmentation results tend to have little change or are even worse than before. To improve the robustness of the response, we propose a structured click intent model based on graph neural networks, which adaptively obtains graph nodes via the global similarity of user-clicked Transformer tokens. …

arxiv click control cs.ai cs.cv interactive segmentation transformer type