AdapterShadow: Adapting Segment Anything Model for Shadow Detection

TL;DR

AdapterShadow effectively adapts the Segment Anything Model for shadow detection by inserting trainable adapters and using a novel grid sampling method for automatic, prompt-free shadow segmentation, demonstrating superior performance on benchmark datasets.

Contribution

It introduces a novel adapter-based approach and grid sampling technique to adapt SAM for shadow detection without manual prompts.

Findings

Superior performance on four benchmark datasets

Automatic shadow segmentation without manual prompts

Efficient adaptation of SAM with trainable adapters

Abstract

Segment anything model (SAM) has shown its spectacular performance in segmenting universal objects, especially when elaborate prompts are provided. However, the drawback of SAM is twofold. On the first hand, it fails to segment specific targets, e.g., shadow images or lesions in medical images. On the other hand, manually specifying prompts is extremely time-consuming. To overcome the problems, we propose AdapterShadow, which adapts SAM model for shadow detection. To adapt SAM for shadow images, trainable adapters are inserted into the frozen image encoder of SAM, since the training of the full SAM model is both time and memory consuming. Moreover, we introduce a novel grid sampling method to generate dense point prompts, which helps to automatically segment shadows without any manual interventions. Extensive experiments are conducted on four widely used benchmark datasets to demonstrate the superior performance of our proposed method. Codes will are publicly available at https://github.com/LeipingJie/AdapterShadow.