摘要
Deep saliency models can effectively imitate the attention mechanism of human vision, and they perform considerably better than classical models that rely on handcrafted features. However, deep models also require higher-level information, such as context or emotional content, to further approach human performance. Therefore, this study proposes a multilevel saliency prediction network that aims to use a combination of spatial and channel information to find possible high-level features, further improving the performance of a saliency model. Firstly, we use a VGG style network with an identity block as the primary network architecture. With the help of re-parameterization, we can obtain rich features similar to multiscale networks and effectively reduce computational cost. Secondly, a subnetwork with a channel attention mechanism is designed to find potential saliency regions and possible high-level semantic information in an image. Finally, image spatial features and a channel enhancement vector are combined after quantization to improve the overall performance of the model. Compared with classical models and other deep models, our model exhibits superior overall performance.
学科与关键词
- Attention-aware concentrated network for saliency predictionLi, Pengqian; Xing, Xiaofen; Xu, Xiangmin*; Cai, Bolun; Cheng, JunNEUROCOMPUTING, 2021, 429: 199-214.被引 8
- Visual Saliency via Selecting and Reweighting Features in Hierarchical Fusion NetworkZhou, Fei; Chen, Junhua; Liu, Bozhi*IEEE SIGNAL PROCESSING LETTERS, 2021, 28: 1749-1753.
- SalED: Saliency prediction with a pithy encoder-decoder architecture sensing local and global informationWang, Ziqiang; Liu, Zhi*; Wei, Weijie; Duan, HuizhanImage and Vision Computing, 2021, 109: 104149.被引 17
