Image segmentation is a challenging task in computer vision that aims to partition an image into distinct regions or objects based on their semantic meaning or visual characteristics. Over the years, numerous methods and algorithms have been developed to tackle this problem, ranging from traditional approaches using handcrafted features to modern deep learning models. Recently, the Segment Anything Model (SAM) has emerged as a groundbreaking vision model capable of segmenting any object within an image based on user interaction prompts. Though powerful, SAM is computationally too demanding, making it challenging to apply in practical scenarios.
