Recursive Multi-model Complementary Deep Fusion forRobust Salient Object Detection via Parallel Sub Networks

TL;DR

This paper introduces a wider, parallel sub-network architecture with dense interactions for salient object detection, achieving superior performance by enhancing feature diversity and complementarity.

Contribution

It proposes a novel wider network with parallel sub-networks and dense short-connections to improve feature diversity and complementarity in salient object detection.

Findings

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

Demonstrates strong generalization across different datasets.

Shows effective feature fusion improves detection accuracy.

Abstract

Fully convolutional networks have shown outstanding performance in the salient object detection (SOD) field. The state-of-the-art (SOTA) methods have a tendency to become deeper and more complex, which easily homogenize their learned deep features, resulting in a clear performance bottleneck. In sharp contrast to the conventional ``deeper'' schemes, this paper proposes a ``wider'' network architecture which consists of parallel sub networks with totally different network architectures. In this way, those deep features obtained via these two sub networks will exhibit large diversity, which will have large potential to be able to complement with each other. However, a large diversity may easily lead to the feature conflictions, thus we use the dense short-connections to enable a recursively interaction between the parallel sub networks, pursuing an optimal complementary status between multi-model deep features. Finally, all these complementary multi-model deep features will be selectively fused to make high-performance salient object detections. Extensive experiments on several famous benchmarks clearly demonstrate the superior performance, good generalization, and powerful learning ability of the proposed wider framework.