Global-Local Feature Decoding with Adapter-Guided SAMv2 for Salient Object Detection

TL;DR

This paper introduces GLASSNet, a novel framework that leverages a frozen foundation model with a dual-decoder architecture to improve salient object detection by combining global semantics and local details.

Contribution

GLASSNet employs a lightweight adapter with SAMv2 as a frozen encoder and a dual-decoder for enhanced global-local feature decoding in SOD.

Findings

GLASSNet surpasses state-of-the-art methods on standard benchmarks.

The adapter reduces learnable parameters by over 97%.

Fusion of global and local cues yields more accurate saliency maps.

Abstract

Salient Object Detection (SOD) remains an essential yet underexplored task in the era of large-scale vision models. Although foundation models like SAM exhibit strong generalization, their potential for SOD is not fully realized, and training or fully fine-tuning them is computationally expensive and prone to overfitting under limited data. To overcome these challenges, we introduce GLASSNet, a Global-Local feature decoding framework that uses SAMv2 as a frozen encoder paired with a lightweight, spatially aware convolutional adapter-reducing learnable encoder parameters by over 97%. To enhance saliency quality, GLASSNet employs a dual-decoder architecture: one decoder captures global, long-range semantics with an expanded receptive field, while the other captures fine local details such as edges and textures. Fusing these complementary cues yields saliency maps that combine global coherence with local precision, producing accurate final masks. Extensive experiments on standard SOD and camouflaged object detection benchmarks show that GLASSNet surpasses state-of-the-art methods, demonstrating the power of frozen foundation models combined with targeted adaptation and global-local decoding.