CPDR: Towards Highly-Efficient Salient Object Detection via Crossed Post-decoder Refinement

TL;DR

This paper introduces CPDR, a lightweight post-decoder refinement module that enhances feature representation in salient object detection models, achieving high efficiency and superior performance on benchmark datasets.

Contribution

The paper proposes a novel crossed post-decoder refinement (CPDR) with attention-based fusion modules that improve feature extraction while reducing parameters.

Findings

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

Reduces model complexity with dual attention cross fusion.

Enhances feature representation in lightweight architectures.

Abstract

Most of the current salient object detection approaches use deeper networks with large backbones to produce more accurate predictions, which results in a significant increase in computational complexity. A great number of network designs follow the pure UNet and Feature Pyramid Network (FPN) architecture which has limited feature extraction and aggregation ability which motivated us to design a lightweight post-decoder refinement module, the crossed post-decoder refinement (CPDR) to enhance the feature representation of a standard FPN or U-Net framework. Specifically, we introduce the Attention Down Sample Fusion (ADF), which employs channel attention mechanisms with attention maps generated by high-level representation to refine the low-level features, and Attention Up Sample Fusion (AUF), leveraging the low-level information to guide the high-level features through spatial attention. Additionally, we proposed the Dual Attention Cross Fusion (DACF) upon ADFs and AUFs, which reduces the number of parameters while maintaining the performance. Experiments on five benchmark datasets demonstrate that our method outperforms previous state-of-the-art approaches.