Existing salient object detection methods often adopt deeper and wider networks for better performance, resulting in heavy computational burden and slow inference speed. This inspires us to rethink saliency detection to achieve a favorable balance between efficiency and accuracy. To this end, we design a lightweight framework while maintaining satisfying competitive accuracy. Specifically, we propose a novel trilateral decoder framework by decoupling the U-shape structure into three complementary branches, which are devised to confront the dilution of semantic context, loss of spatial structure and absence of boundary detail, respectively. Along with the fusion of three branches, the coarse segmentation results are gradually refined in structure details and boundary quality. Without adding additional learnable parameters, we further propose Scale-Adaptive Pooling Module to obtain multi-scale receptive filed. In particular, on the premise of inheriting this framework, we rethink the relationship among accuracy, parameters and speed via network depth-width tradeoff. With these insightful considerations, we comprehensively design shallower and narrower models to explore the maximum potential of lightweight SOD. Our models are purposed for different application environments: 1) a tiny version CTD-S (1.7M, 125FPS) for resource constrained devices, 2) a fast version CTD-M (12.6M, 158FPS) for speed-demanding scenarios, 3) a standard version CTD-L (26.5M, 84FPS) for high-performance platforms. Extensive experiments validate the superiority of our method, which achieves better efficiency-accuracy balance across five benchmarks.
翻译:现有显著物体探测方法往往采用更深、更广的网络来提高性能,造成沉重的计算负担和缓慢的推导速度。这促使我们重新思考显著的探测方法,以便在效率和准确性之间取得有利的平衡。为此,我们设计了一个轻量框架,同时保持竞争准确性。具体地说,我们提议了一个全新的三边解码框架,将U形结构分解成三个互补的分支,分别是为了应对语义背景的分解、空间结构的丧失和边界细节的缺失。随着三个分支的合并,粗度的分解结果在结构细节和边界质量方面逐步得到完善。我们不增加可学习参数,我们进一步提议一个规模化的组合模块,以获得多尺度的接受性意见。特别是,我们从继承这一框架的前提出发,我们重新思考了准确性、参数和速度之间的关系。我们全面设计了更浅度和更窄的模型,以探索轻度的SOD的最大潜力。我们的模型用于不同应用环境:1个小版本的CTD-M-Rioral-C-CTD-Callicalal 5 S 标准(12M-FP),用于快速的CTD-CTD-CTD-CTD-C-L) AS-ralal-ralalalal 3 标准型的CTD-C1-C-FP-S 格式,用于快速的C1-C1-SG-C1-25FP-ral-C1-25-C-C-FA-ral-FS) 标准级版本,高版本的S-C-C-CTD-FS-C1-C1-C-C-C1-SG-FS-3) 格式的精确性平价制版。