An Efficient Module for Instance Segmentation Based on Multi-Level Features and Attention Mechanisms
Recently, multi-level feature networks have been extensively used in instance segmentation. However, because not all features are beneficial to instance segmentation tasks, the performance of networks cannot be adequately improved by synthesizing multi-level convolutional features indiscriminately....
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-01-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/11/3/968 |
| _version_ | 1797408791280484352 |
|---|---|
| author | Yingchun Sun Wang Gao Shuguo Pan Tao Zhao Yahui Peng |
| author_facet | Yingchun Sun Wang Gao Shuguo Pan Tao Zhao Yahui Peng |
| author_sort | Yingchun Sun |
| collection | DOAJ |
| description | Recently, multi-level feature networks have been extensively used in instance segmentation. However, because not all features are beneficial to instance segmentation tasks, the performance of networks cannot be adequately improved by synthesizing multi-level convolutional features indiscriminately. In order to solve the problem, an attention-based feature pyramid module (AFPM) is proposed, which integrates the attention mechanism on the basis of a multi-level feature pyramid network to efficiently and pertinently extract the high-level semantic features and low-level spatial structure features; for instance, segmentation. Firstly, we adopt a convolutional block attention module (CBAM) into feature extraction, and sequentially generate attention maps which focus on instance-related features along the channel and spatial dimensions. Secondly, we build inter-dimensional dependencies through a convolutional triplet attention module (CTAM) in lateral attention connections, which is used to propagate a helpful semantic feature map and filter redundant informative features irrelevant to instance objects. Finally, we construct branches for feature enhancement to strengthen detailed information to boost the entire feature hierarchy of the network. The experimental results on the Cityscapes dataset manifest that the proposed module outperforms other excellent methods under different evaluation metrics and effectively upgrades the performance of the instance segmentation method. |
| first_indexed | 2024-03-09T04:04:40Z |
| format | Article |
| id | doaj.art-866e3cdd3b804471b5c3f648a172c797 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T04:04:40Z |
| publishDate | 2021-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-866e3cdd3b804471b5c3f648a172c7972023-12-03T14:08:38ZengMDPI AGApplied Sciences2076-34172021-01-0111396810.3390/app11030968An Efficient Module for Instance Segmentation Based on Multi-Level Features and Attention MechanismsYingchun Sun0Wang Gao1Shuguo Pan2Tao Zhao3Yahui Peng4School of Instrument Science and Engineering, Southeast University, Nanjing 210096, ChinaSchool of Instrument Science and Engineering, Southeast University, Nanjing 210096, ChinaSchool of Instrument Science and Engineering, Southeast University, Nanjing 210096, ChinaSchool of Instrument Science and Engineering, Southeast University, Nanjing 210096, ChinaSchool of Instrument Science and Engineering, Southeast University, Nanjing 210096, ChinaRecently, multi-level feature networks have been extensively used in instance segmentation. However, because not all features are beneficial to instance segmentation tasks, the performance of networks cannot be adequately improved by synthesizing multi-level convolutional features indiscriminately. In order to solve the problem, an attention-based feature pyramid module (AFPM) is proposed, which integrates the attention mechanism on the basis of a multi-level feature pyramid network to efficiently and pertinently extract the high-level semantic features and low-level spatial structure features; for instance, segmentation. Firstly, we adopt a convolutional block attention module (CBAM) into feature extraction, and sequentially generate attention maps which focus on instance-related features along the channel and spatial dimensions. Secondly, we build inter-dimensional dependencies through a convolutional triplet attention module (CTAM) in lateral attention connections, which is used to propagate a helpful semantic feature map and filter redundant informative features irrelevant to instance objects. Finally, we construct branches for feature enhancement to strengthen detailed information to boost the entire feature hierarchy of the network. The experimental results on the Cityscapes dataset manifest that the proposed module outperforms other excellent methods under different evaluation metrics and effectively upgrades the performance of the instance segmentation method.https://www.mdpi.com/2076-3417/11/3/968AFPMmulti-level featuresinter-dimensional interactionattention mechanisminstance segmentation |
| spellingShingle | Yingchun Sun Wang Gao Shuguo Pan Tao Zhao Yahui Peng An Efficient Module for Instance Segmentation Based on Multi-Level Features and Attention Mechanisms Applied Sciences AFPM multi-level features inter-dimensional interaction attention mechanism instance segmentation |
| title | An Efficient Module for Instance Segmentation Based on Multi-Level Features and Attention Mechanisms |
| title_full | An Efficient Module for Instance Segmentation Based on Multi-Level Features and Attention Mechanisms |
| title_fullStr | An Efficient Module for Instance Segmentation Based on Multi-Level Features and Attention Mechanisms |
| title_full_unstemmed | An Efficient Module for Instance Segmentation Based on Multi-Level Features and Attention Mechanisms |
| title_short | An Efficient Module for Instance Segmentation Based on Multi-Level Features and Attention Mechanisms |
| title_sort | efficient module for instance segmentation based on multi level features and attention mechanisms |
| topic | AFPM multi-level features inter-dimensional interaction attention mechanism instance segmentation |
| url | https://www.mdpi.com/2076-3417/11/3/968 |
| work_keys_str_mv | AT yingchunsun anefficientmoduleforinstancesegmentationbasedonmultilevelfeaturesandattentionmechanisms AT wanggao anefficientmoduleforinstancesegmentationbasedonmultilevelfeaturesandattentionmechanisms AT shuguopan anefficientmoduleforinstancesegmentationbasedonmultilevelfeaturesandattentionmechanisms AT taozhao anefficientmoduleforinstancesegmentationbasedonmultilevelfeaturesandattentionmechanisms AT yahuipeng anefficientmoduleforinstancesegmentationbasedonmultilevelfeaturesandattentionmechanisms AT yingchunsun efficientmoduleforinstancesegmentationbasedonmultilevelfeaturesandattentionmechanisms AT wanggao efficientmoduleforinstancesegmentationbasedonmultilevelfeaturesandattentionmechanisms AT shuguopan efficientmoduleforinstancesegmentationbasedonmultilevelfeaturesandattentionmechanisms AT taozhao efficientmoduleforinstancesegmentationbasedonmultilevelfeaturesandattentionmechanisms AT yahuipeng efficientmoduleforinstancesegmentationbasedonmultilevelfeaturesandattentionmechanisms |