计算机科学
突出
水准点(测量)
人工智能
特征(语言学)
像素
功能(生物学)
骨料(复合)
模式识别(心理学)
过程(计算)
目标检测
对象(语法)
计算机视觉
语言学
哲学
材料科学
大地测量学
进化生物学
复合材料
生物
地理
操作系统
作者
Sheng Yang,Weisi Lin,Guosheng Lin,Qiuping Jiang,Zichuan Liu
标识
DOI:10.1109/tip.2021.3113794
摘要
We present a simple yet effective progressive self-guided loss function to facilitate deep learning-based salient object detection (SOD) in images. The saliency maps produced by the most relevant works still suffer from incomplete predictions due to the internal complexity of salient objects. Our proposed progressive self-guided loss simulates a morphological closing operation on the model predictions for progressively creating auxiliary training supervisions to step-wisely guide the training process. We demonstrate that this new loss function can guide the SOD model to highlight more complete salient objects step-by-step and meanwhile help to uncover the spatial dependencies of the salient object pixels in a region growing manner. Moreover, a new feature aggregation module is proposed to capture multi-scale features and aggregate them adaptively by a branch-wise attention mechanism. Benefiting from this module, our SOD framework takes advantage of adaptively aggregated multi-scale features to locate and detect salient objects effectively. Experimental results on several benchmark datasets show that our loss function not only advances the performance of existing SOD models without architecture modification but also helps our proposed framework to achieve state-of-the-art performance.
科研通智能强力驱动
Strongly Powered by AbleSci AI