A Saliency Prediction Model Based on Re-Parameterization and Channel Attention Mechanism
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 hu...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-04-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/11/8/1180 |
| _version_ | 1797446734165573632 |
|---|---|
| author | Fei Yan Zhiliang Wang Siyu Qi Ruoxiu Xiao |
| author_facet | Fei Yan Zhiliang Wang Siyu Qi Ruoxiu Xiao |
| author_sort | Fei Yan |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-09T13:44:50Z |
| format | Article |
| id | doaj.art-0454bafa3614444d83a3805b25a8f256 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-09T13:44:50Z |
| publishDate | 2022-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-0454bafa3614444d83a3805b25a8f2562023-11-30T21:01:28ZengMDPI AGElectronics2079-92922022-04-01118118010.3390/electronics11081180A Saliency Prediction Model Based on Re-Parameterization and Channel Attention MechanismFei Yan0Zhiliang Wang1Siyu Qi2Ruoxiu Xiao3School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing 100083, ChinaSchool of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing 100083, ChinaSchool of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing 100083, ChinaSchool of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing 100083, ChinaDeep 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.https://www.mdpi.com/2079-9292/11/8/1180visual attentionvisual saliencysaliency predictiondeep learningre-parameterization |
| spellingShingle | Fei Yan Zhiliang Wang Siyu Qi Ruoxiu Xiao A Saliency Prediction Model Based on Re-Parameterization and Channel Attention Mechanism Electronics visual attention visual saliency saliency prediction deep learning re-parameterization |
| title | A Saliency Prediction Model Based on Re-Parameterization and Channel Attention Mechanism |
| title_full | A Saliency Prediction Model Based on Re-Parameterization and Channel Attention Mechanism |
| title_fullStr | A Saliency Prediction Model Based on Re-Parameterization and Channel Attention Mechanism |
| title_full_unstemmed | A Saliency Prediction Model Based on Re-Parameterization and Channel Attention Mechanism |
| title_short | A Saliency Prediction Model Based on Re-Parameterization and Channel Attention Mechanism |
| title_sort | saliency prediction model based on re parameterization and channel attention mechanism |
| topic | visual attention visual saliency saliency prediction deep learning re-parameterization |
| url | https://www.mdpi.com/2079-9292/11/8/1180 |
| work_keys_str_mv | AT feiyan asaliencypredictionmodelbasedonreparameterizationandchannelattentionmechanism AT zhiliangwang asaliencypredictionmodelbasedonreparameterizationandchannelattentionmechanism AT siyuqi asaliencypredictionmodelbasedonreparameterizationandchannelattentionmechanism AT ruoxiuxiao asaliencypredictionmodelbasedonreparameterizationandchannelattentionmechanism AT feiyan saliencypredictionmodelbasedonreparameterizationandchannelattentionmechanism AT zhiliangwang saliencypredictionmodelbasedonreparameterizationandchannelattentionmechanism AT siyuqi saliencypredictionmodelbasedonreparameterizationandchannelattentionmechanism AT ruoxiuxiao saliencypredictionmodelbasedonreparameterizationandchannelattentionmechanism |