期刊
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
卷 32, 期 3, 页码 1378-1389出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TCSVT.2021.3069848
关键词
Feature extraction; Object detection; Decoding; Semantics; Kernel; Visualization; Task analysis; Salient object detection; dense context exploration; attentive skip-connection
资金
- National Natural Science Foundation of China [91748104, 61972067, U1908214]
- Innovation Technology Funding of Dalian [2020JJ26GX036]
This paper explores an effective and efficient method for learning rich contexts for accurate salient object detection. By constructing a dense context exploration module and embedding multiple modules in an encoder-decoder architecture, the proposed method achieves better results by extracting contexts of different levels and utilizing attention skip-connections for feature transmission.
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.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据