FIPGNet:Pyramid grafting network with feature interaction strategies

TL;DR

FIPGNet introduces a pyramid grafting network with feature interaction strategies, utilizing spatial and channel attention mechanisms to improve salient object detection accuracy by effectively modeling multi-scale feature correlations.

Contribution

The paper proposes a novel salience detection framework that incorporates spatial and channel attention modules for enhanced multi-scale feature interaction, addressing limitations of existing pyramid grafting networks.

Findings

Outperforms 12 state-of-the-art methods on four metrics

Achieves superior accuracy on six challenging datasets

Effectively models multi-scale feature correlations

Abstract

Salient object detection is designed to identify the objects in an image that attract the most visual attention.Currently, the most advanced method of significance object detection adopts pyramid grafting network architecture.However, pyramid-graft network architecture still has the problem of failing to accurately locate significant targets.We observe that this is mainly due to the fact that current salient object detection methods simply aggregate different scale features, ignoring the correlation between different scale features.To overcome these problems, we propose a new salience object detection framework(FIPGNet),which is a pyramid graft network with feature interaction strategies.Specifically, we propose an attention-mechanism based feature interaction strategy (FIA) that innovatively introduces spatial agent Cross Attention (SACA) to achieve multi-level feature interaction, highlighting important spatial regions from a spatial perspective, thereby enhancing salient regions.And the channel proxy Cross Attention Module (CCM), which is used to effectively connect the features extracted by the backbone network and the features processed using the spatial proxy cross attention module, eliminating inconsistencies.Finally, under the action of these two modules, the prominent target location problem in the current pyramid grafting network model is solved.Experimental results on six challenging datasets show that the proposed method outperforms the current 12 salient object detection methods on four indicators.