Can SAM Segment Anything? When SAM Meets Camouflaged Object Detection
Lv Tang, Haoke Xiao, Bo Li
TL;DR
This paper investigates whether the Segment Anything Model (SAM) can address camouflaged object detection (COD) by evaluating SAM on COD benchmarks using maximum segmentation evaluation and camouflage location evaluation, and by comparing its performance to 22 COD methods. It leverages datasets CAMO, COD10K, and NC4K with six standard COD metrics to assess upper-bound segmentation and localization capabilities. The results indicate that SAM, while strong in generic segmentation, has limited COD performance relative to state-of-the-art COD methods, highlighting a gap to be filled by future work. The study motivates adapting foundation models like SAM for COD tasks and suggests architectural or training adjustments to improve camouflage detection.
Abstract
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}.