Double Branch Attention Block for Discriminative Representation of Siamese Trackers
Siamese trackers have achieved a good balance between accuracy and efficiency in generic object tracking. However, background distractors cause side effects to the discriminative representation of the target. To suppress the sensitivity of trackers to background distractors, we propose a Double Bran...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-03-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/6/2897 |
| _version_ | 1797473088693075968 |
|---|---|
| author | Jiaqi Xi Jin Yang Xiaodong Chen Yi Wang Huaiyu Cai |
| author_facet | Jiaqi Xi Jin Yang Xiaodong Chen Yi Wang Huaiyu Cai |
| author_sort | Jiaqi Xi |
| collection | DOAJ |
| description | Siamese trackers have achieved a good balance between accuracy and efficiency in generic object tracking. However, background distractors cause side effects to the discriminative representation of the target. To suppress the sensitivity of trackers to background distractors, we propose a Double Branch Attention (DBA) block and a Siamese tracker equipped with the DBA block named DBA-Siam. First, the DBA block concatenates channels of multiple layers from two branches of the Siamese framework to obtain rich feature representation. Second, the channel attention is applied to the two concatenated feature blocks to enhance the robust features selectively, thus enhancing the ability to distinguish the target from the complex background. Finally, the DBA block collects the contextual relevance between the Siamese branches and adaptively encodes it into the feature weight of the detection branch for information compensation. Ablation experiments show that the proposed block can enhance the discriminative representation of the target and significantly improve the tracking performance. Results on two popular benchmarks show that DBA-Siam performs favorably against its counterparts. Compared with the advanced algorithm CSTNet, DBA-Siam improves the EAO by 18.9% on VOT2016. |
| first_indexed | 2024-03-09T20:10:06Z |
| format | Article |
| id | doaj.art-ce2e8dad7cbc40169c25d9510c75b240 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T20:10:06Z |
| publishDate | 2022-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-ce2e8dad7cbc40169c25d9510c75b2402023-11-24T00:20:57ZengMDPI AGApplied Sciences2076-34172022-03-01126289710.3390/app12062897Double Branch Attention Block for Discriminative Representation of Siamese TrackersJiaqi Xi0Jin Yang1Xiaodong Chen2Yi Wang3Huaiyu Cai4Key Laboratory of Photoelectric Information, Ministry of Education, School of Precision Instruments and Optoelectronic Engineering, Tianjin University, Tianjin 300072, ChinaKey Laboratory of Photoelectric Information, Ministry of Education, School of Precision Instruments and Optoelectronic Engineering, Tianjin University, Tianjin 300072, ChinaKey Laboratory of Photoelectric Information, Ministry of Education, School of Precision Instruments and Optoelectronic Engineering, Tianjin University, Tianjin 300072, ChinaKey Laboratory of Photoelectric Information, Ministry of Education, School of Precision Instruments and Optoelectronic Engineering, Tianjin University, Tianjin 300072, ChinaKey Laboratory of Photoelectric Information, Ministry of Education, School of Precision Instruments and Optoelectronic Engineering, Tianjin University, Tianjin 300072, ChinaSiamese trackers have achieved a good balance between accuracy and efficiency in generic object tracking. However, background distractors cause side effects to the discriminative representation of the target. To suppress the sensitivity of trackers to background distractors, we propose a Double Branch Attention (DBA) block and a Siamese tracker equipped with the DBA block named DBA-Siam. First, the DBA block concatenates channels of multiple layers from two branches of the Siamese framework to obtain rich feature representation. Second, the channel attention is applied to the two concatenated feature blocks to enhance the robust features selectively, thus enhancing the ability to distinguish the target from the complex background. Finally, the DBA block collects the contextual relevance between the Siamese branches and adaptively encodes it into the feature weight of the detection branch for information compensation. Ablation experiments show that the proposed block can enhance the discriminative representation of the target and significantly improve the tracking performance. Results on two popular benchmarks show that DBA-Siam performs favorably against its counterparts. Compared with the advanced algorithm CSTNet, DBA-Siam improves the EAO by 18.9% on VOT2016.https://www.mdpi.com/2076-3417/12/6/2897object trackingSiamese frameworkself-attention mechanism |
| spellingShingle | Jiaqi Xi Jin Yang Xiaodong Chen Yi Wang Huaiyu Cai Double Branch Attention Block for Discriminative Representation of Siamese Trackers Applied Sciences object tracking Siamese framework self-attention mechanism |
| title | Double Branch Attention Block for Discriminative Representation of Siamese Trackers |
| title_full | Double Branch Attention Block for Discriminative Representation of Siamese Trackers |
| title_fullStr | Double Branch Attention Block for Discriminative Representation of Siamese Trackers |
| title_full_unstemmed | Double Branch Attention Block for Discriminative Representation of Siamese Trackers |
| title_short | Double Branch Attention Block for Discriminative Representation of Siamese Trackers |
| title_sort | double branch attention block for discriminative representation of siamese trackers |
| topic | object tracking Siamese framework self-attention mechanism |
| url | https://www.mdpi.com/2076-3417/12/6/2897 |
| work_keys_str_mv | AT jiaqixi doublebranchattentionblockfordiscriminativerepresentationofsiamesetrackers AT jinyang doublebranchattentionblockfordiscriminativerepresentationofsiamesetrackers AT xiaodongchen doublebranchattentionblockfordiscriminativerepresentationofsiamesetrackers AT yiwang doublebranchattentionblockfordiscriminativerepresentationofsiamesetrackers AT huaiyucai doublebranchattentionblockfordiscriminativerepresentationofsiamesetrackers |