Assisting human annotation of marine images with foundation models

Eric Orenstein^1,2*Benjamin Woodward³Lonny J Lundsten¹Kevin Scott Barnard¹Brian Schlining¹Kakani Katija¹

• ¹Monterey Bay Aquarium Research Institute (MBARI), Moss Landing, United States
• ²National Oceanography Centre, Southampton, United Kingdom
• ³CVision AI, Medford, MA, United States

Marine scientists have been leveraging supervised machine learning algorithms to analyze image and video data for nearly two decades. There have been many advances, but the cost of generating expert human annotations to train new models remains extremely high. There is broad recognition both in computer and domain sciences that generating training data remains the major bottleneck when developing ML models for targeted tasks. Increasingly, computer scientists are not attempting to produce highly-optimized models from general annotation frameworks, instead focusing on adaptation strategies to tackle new data challenges. Taking inspiration from large language models, computer vision researchers are now thinking in terms of "foundation models" that can yield reasonable zero-and few-shot detection and segmentation performance with human prompting. Here we consider the utility of this approach for ocean imagery, leveraging Meta's Segment Anything Model to enrich ocean image annotations based on existing labels. This workflow yields promising results, especially for modernizing existing data repositories. Moreover, it suggests that future human annotation efforts could use foundation models to speed progress towards a sufficient training set to address domain specific problems.