Target State Classification by Attention-Based Branch Expansion Network
The intelligent laboratory is an important carrier for the development of the manufacturing industry. In order to meet the technical state requirements of the laboratory and control the particle redundancy, the wearing state of personnel and the technical state of objects are very important observat...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-10-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/11/21/10208 |
| _version_ | 1797512763692548096 |
|---|---|
| author | Yue Zhang Shengli Sun Huikai Liu Linjian Lei Gaorui Liu Dehui Lu |
| author_facet | Yue Zhang Shengli Sun Huikai Liu Linjian Lei Gaorui Liu Dehui Lu |
| author_sort | Yue Zhang |
| collection | DOAJ |
| description | The intelligent laboratory is an important carrier for the development of the manufacturing industry. In order to meet the technical state requirements of the laboratory and control the particle redundancy, the wearing state of personnel and the technical state of objects are very important observation indicators in the digital laboratory. We collect human and object state datasets, which present the state classification challenge of the staff and experimental tools. Humans and objects are especially important for scene understanding, especially those existing in scenarios that have an impact on the current task. Based on the characteristics of the above datasets—small inter-class distance and large intra-class distance—an attention-based branch expansion network (ABE) is proposed to distinguish confounding features. In order to achieve the best recognition effect by considering the network’s depth and width, we firstly carry out a multi-dimensional reorganization of the existing network structure to explore the influence of depth and width on feature expression by comparing four networks with different depths and widths. We apply channel and spatial attention to refine the features extracted by the four networks, which learn “what” and “where”, respectively, to focus. We find the best results lie in the parallel residual connection of the dual attention applied in stacked block mode. We conduct extensive ablation analysis, gain consistent improvements in classification performance on various datasets, demonstrate the effectiveness of the dual-attention-based branch expansion network, and show a wide range of applicability. It achieves comparable performance with the state of the art (SOTA) on the common dataset Trashnet, with an accuracy of 94.53%. |
| first_indexed | 2024-03-10T06:06:18Z |
| format | Article |
| id | doaj.art-3098baac85724df995c5b4e67fc49c6a |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T06:06:18Z |
| publishDate | 2021-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-3098baac85724df995c5b4e67fc49c6a2023-11-22T20:29:23ZengMDPI AGApplied Sciences2076-34172021-10-0111211020810.3390/app112110208Target State Classification by Attention-Based Branch Expansion NetworkYue Zhang0Shengli Sun1Huikai Liu2Linjian Lei3Gaorui Liu4Dehui Lu5Shanghai Institute of Technical Physics, Chinese Academy of Sciences, Shanghai 200083, ChinaShanghai Institute of Technical Physics, Chinese Academy of Sciences, Shanghai 200083, ChinaShanghai Institute of Technical Physics, Chinese Academy of Sciences, Shanghai 200083, ChinaShanghai Institute of Technical Physics, Chinese Academy of Sciences, Shanghai 200083, ChinaShanghai Institute of Technical Physics, Chinese Academy of Sciences, Shanghai 200083, ChinaShanghai Institute of Technical Physics, Chinese Academy of Sciences, Shanghai 200083, ChinaThe intelligent laboratory is an important carrier for the development of the manufacturing industry. In order to meet the technical state requirements of the laboratory and control the particle redundancy, the wearing state of personnel and the technical state of objects are very important observation indicators in the digital laboratory. We collect human and object state datasets, which present the state classification challenge of the staff and experimental tools. Humans and objects are especially important for scene understanding, especially those existing in scenarios that have an impact on the current task. Based on the characteristics of the above datasets—small inter-class distance and large intra-class distance—an attention-based branch expansion network (ABE) is proposed to distinguish confounding features. In order to achieve the best recognition effect by considering the network’s depth and width, we firstly carry out a multi-dimensional reorganization of the existing network structure to explore the influence of depth and width on feature expression by comparing four networks with different depths and widths. We apply channel and spatial attention to refine the features extracted by the four networks, which learn “what” and “where”, respectively, to focus. We find the best results lie in the parallel residual connection of the dual attention applied in stacked block mode. We conduct extensive ablation analysis, gain consistent improvements in classification performance on various datasets, demonstrate the effectiveness of the dual-attention-based branch expansion network, and show a wide range of applicability. It achieves comparable performance with the state of the art (SOTA) on the common dataset Trashnet, with an accuracy of 94.53%.https://www.mdpi.com/2076-3417/11/21/10208technical state requirementstarget state classificationbranch expansiondual-attention moduleparallel residual connectionstacked block |
| spellingShingle | Yue Zhang Shengli Sun Huikai Liu Linjian Lei Gaorui Liu Dehui Lu Target State Classification by Attention-Based Branch Expansion Network Applied Sciences technical state requirements target state classification branch expansion dual-attention module parallel residual connection stacked block |
| title | Target State Classification by Attention-Based Branch Expansion Network |
| title_full | Target State Classification by Attention-Based Branch Expansion Network |
| title_fullStr | Target State Classification by Attention-Based Branch Expansion Network |
| title_full_unstemmed | Target State Classification by Attention-Based Branch Expansion Network |
| title_short | Target State Classification by Attention-Based Branch Expansion Network |
| title_sort | target state classification by attention based branch expansion network |
| topic | technical state requirements target state classification branch expansion dual-attention module parallel residual connection stacked block |
| url | https://www.mdpi.com/2076-3417/11/21/10208 |
| work_keys_str_mv | AT yuezhang targetstateclassificationbyattentionbasedbranchexpansionnetwork AT shenglisun targetstateclassificationbyattentionbasedbranchexpansionnetwork AT huikailiu targetstateclassificationbyattentionbasedbranchexpansionnetwork AT linjianlei targetstateclassificationbyattentionbasedbranchexpansionnetwork AT gaoruiliu targetstateclassificationbyattentionbasedbranchexpansionnetwork AT dehuilu targetstateclassificationbyattentionbasedbranchexpansionnetwork |