MAIS: Memory-Attention for Interactive Segmentation
This addresses the need for reduced annotation effort in medical imaging by improving interactive segmentation, though it appears incremental as it builds on existing Vision Transformer-based models like SAM.
The paper tackled the problem of redundant corrections and limited refinement gains in interactive medical segmentation by introducing MAIS, a Memory-Attention mechanism that stores past user inputs and segmentation states for temporal context integration, achieving more efficient and accurate refinements.
Interactive medical segmentation reduces annotation effort by refining predictions through user feedback. Vision Transformer (ViT)-based models, such as the Segment Anything Model (SAM), achieve state-of-the-art performance using user clicks and prior masks as prompts. However, existing methods treat interactions as independent events, leading to redundant corrections and limited refinement gains. We address this by introducing MAIS, a Memory-Attention mechanism for Interactive Segmentation that stores past user inputs and segmentation states, enabling temporal context integration. Our approach enhances ViT-based segmentation across diverse imaging modalities, achieving more efficient and accurate refinements.