Can SAM Segment Anything? When SAM Meets Camouflaged Object Detection
This work identifies a specific weakness in SAM for camouflaged object detection, which has applications in medicine, art, and agriculture, but is incremental as it primarily benchmarks an existing model.
The study evaluated SAM's performance on camouflaged object detection (COD) tasks, finding that while SAM excels in generic segmentation, it performs poorly on COD benchmarks compared to 22 state-of-the-art methods, indicating limitations in handling camouflaged scenes.
SAM is a segmentation model recently released by Meta AI Research and has been gaining attention quickly due to its impressive performance in generic object segmentation. However, its ability to generalize to specific scenes such as camouflaged scenes is still unknown. Camouflaged object detection (COD) involves identifying objects that are seamlessly integrated into their surroundings and has numerous practical applications in fields such as medicine, art, and agriculture. In this study, we try to ask if SAM can address the COD task and evaluate the performance of SAM on the COD benchmark by employing maximum segmentation evaluation and camouflage location evaluation. We also compare SAM's performance with 22 state-of-the-art COD methods. Our results indicate that while SAM shows promise in generic object segmentation, its performance on the COD task is limited. This presents an opportunity for further research to explore how to build a stronger SAM that may address the COD task. The results of this paper are provided in \url{https://github.com/luckybird1994/SAMCOD}.