Exploring Dense Context for Salient Object Detection
Exploring Dense Context for Salient Object Detection
复制标题
DOI：
10.1109/tcsvt.2021.3069848
复制
发表时间：
2021-03
影响因子：
8.4
通讯作者：
Haiyang Mei;Liu Yuanyuan;Ziqi Wei;Li Zhu;Yuxin Wang;D. Zhou;Qiang Zhang;Xin Yang
中科院分区：
文献类型：
--
作者：
Haiyang Mei;Liu Yuanyuan;Ziqi Wei;Li Zhu;Yuxin Wang;D. Zhou;Qiang Zhang;Xin Yang
上下文在显著对象检测(SOD)中起着重要作用。高层上下文描述不同部分/对象之间的关系，从而有助于发现显著对象的特定位置，而低级上下文可以提供用于描绘显著对象边界的精细细节信息。然而，现有的超氧化物歧义理论著作还没有对感知/利用丰富语境的方式进行充分的研究。常见的上下文提取策略(例如，利用具有大核的卷积或具有大扩张率的Arous卷积)没有同时考虑有效性和效率，并且可能导致次优解。在本文中，我们致力于探索一种有效和高效的方法来学习准确的SOD的丰富上下文。具体地说，我们首先构建密集上下文探索(DCE)模块来捕获密集的多尺度上下文，并进一步利用学习的上下文来增强特征的区分性。然后，我们在编解码器架构中嵌入多个DCE模块，以获取不同级别的密集上下文。此外，我们提出了一种细心的跳跃连接，将有用的特征从编码器部分传输到解码部分，以便更好地进行密集上下文探索。大量实验表明，该方法在6个基准数据集上的检测结果优于18种最新的超氧化物歧化方法。
Contexts play an important role in salient object detection (SOD). High-level contexts describe the relations between different parts/objects and thus are helpful for discovering the specific locations of salient objects while low-level contexts could provide the fine detail information for delineating the boundary of the salient objects. However, the way of perceiving/leveraging rich contexts has not been fully investigated by existing SOD works. The common context extraction strategies (e.g., leveraging convolutions with large kernels or atrous convolutions with large dilation rates) do not consider the effectiveness and efficiency simultaneously and may cause sub-optimal solutions. In this paper, we devote to exploring an effective and efficient way to learn rich contexts for accurate SOD. Specifically, we first build a dense context exploration (DCE) module to capture dense multi-scale contexts and further leverage the learned contexts to enhance the features discriminability. Then, we embed multiple DCE modules in an encoder-decoder architecture to harvest dense contexts of different levels. Furthermore, we propose an attentive skip-connection to transmit useful features from the encoder part to the decoder part for better dense context exploration. Finally, extensive experiments demonstrate that the proposed method achieves more superior detection results on the six benchmark datasets than 18 state-of-the-art SOD methods.