Guardado en:
Detalles Bibliográficos
Autores principales: Xu, Long, Li, Shanghong, Chen, Yongquan, Luo, Jun, Lai, Shiwu
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2401.04403
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
Tabla de Contenidos:
  • Interactive segmentation has gained significant attention for its application in human-computer interaction and data annotation. To address the target scale variation issue in interactive segmentation, a novel multi-scale token adaptation algorithm is proposed. By performing top-k operations across multi-scale tokens, the computational complexity is greatly simplified while ensuring performance. To enhance the robustness of multi-scale token selection, we also propose a token learning algorithm based on contrastive loss. This algorithm can effectively improve the performance of multi-scale token adaptation. Extensive benchmarking shows that the algorithm achieves state-of-the-art (SOTA) performance, compared to current methods. An interactive demo and all reproducible codes will be released at https://github.com/hahamyt/mst.