arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2008.04158cs.CVcs.LG
收藏

基于并行子网络的递归多模型互补深度融合forRobust显著目标检测

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

Beihang University(北京航空航天大学);Qingdao University(青岛大学);Stonybrook University(石溪大学)

Zhenyu Wu, Shuai Li, Chenglizhao Chen, Aimin Hao, Hong Qin

摘要:

全卷积网络在显著目标检测(SOD)领域表现出了出色的性能。最先进的(SOTA)方法倾向于变得更深入和更复杂,这很容易使它们学习到的深度特征同质化,从而导致明显的性能瓶颈。与传统的“更深”方案形成鲜明对比的是,本文提出了一种“更宽”的网络结构,它由具有完全不同网络结构的并行子网组成。通过这种方式,通过这两个子网络获得的这些深度特征将表现出很大的多样性,这将具有很大的潜力,能够相互补充。然而,多样性过大容易导致特征冲突,因此我们使用密集短连接来实现并行子网络之间的递归交互,追求多模型深度特征之间的最佳互补状态。最后,所有这些互补的多模型深度特征将被选择性地融合,以进行高性能的显著目标检测。在几个著名的基准测试上的大量实验清楚地表明了所提出的更广泛的框架的优越性能,良好的泛化能力和强大的学习能力。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑