Adapting the Segment Anything Model During Usage in Novel Situations
This addresses the limitation of foundation models like SAM for immediate applicability in interactive segmentation tasks, though it is incremental as it builds on SAM.
The paper tackles the problem of the Segment Anything Model (SAM) failing in interactive segmentation on novel domains or object types, with a failure rate up to 72.6%, and presents a framework that adapts SAM during usage, achieving relative reductions of up to 48.1% and 46.6% in failure metrics.
The interactive segmentation task consists in the creation of object segmentation masks based on user interactions. The most common way to guide a model towards producing a correct segmentation consists in clicks on the object and background. The recently published Segment Anything Model (SAM) supports a generalized version of the interactive segmentation problem and has been trained on an object segmentation dataset which contains 1.1B masks. Though being trained extensively and with the explicit purpose of serving as a foundation model, we show significant limitations of SAM when being applied for interactive segmentation on novel domains or object types. On the used datasets, SAM displays a failure rate $\text{FR}_{30}@90$ of up to $72.6 \%$. Since we still want such foundation models to be immediately applicable, we present a framework that can adapt SAM during immediate usage. For this we will leverage the user interactions and masks, which are constructed during the interactive segmentation process. We use this information to generate pseudo-labels, which we use to compute a loss function and optimize a part of the SAM model. The presented method causes a relative reduction of up to $48.1 \%$ in the $\text{FR}_{20}@85$ and $46.6 \%$ in the $\text{FR}_{30}@90$ metrics.