Adaptive Low Rank Adaptation of Segment Anything to Salient Object Detection

TL;DR

This paper introduces SSOM, an adaptive method that fine-tunes the Segment Anything Model to improve salient object detection, leveraging low-rank structures for enhanced performance across multiple benchmarks.

Contribution

It presents a novel adaptive fine-tuning approach for SAM specifically tailored to salient object detection, utilizing low-rank structures for better accuracy.

Findings

Outperforms state-of-the-art methods on five RGB benchmark datasets

Demonstrates superior qualitative and quantitative results

Effectively adapts SAM for salient object detection

Abstract

Foundation models, such as OpenAI's GPT-3 and GPT-4, Meta's LLaMA, and Google's PaLM2, have revolutionized the field of artificial intelligence. A notable paradigm shift has been the advent of the Segment Anything Model (SAM), which has exhibited a remarkable capability to segment real-world objects, trained on 1 billion masks and 11 million images. Although SAM excels in general object segmentation, it lacks the intrinsic ability to detect salient objects, resulting in suboptimal performance in this domain. To address this challenge, we present the Segment Salient Object Model (SSOM), an innovative approach that adaptively fine-tunes SAM for salient object detection by harnessing the low-rank structure inherent in deep learning. Comprehensive qualitative and quantitative evaluations across five challenging RGB benchmark datasets demonstrate the superior performance of our approach, surpassing state-of-the-art methods.