Back to Search
Start Over
EAPT: Efficient Attention Pyramid Transformer for Image Processing
- Source :
- IEEE Transactions on Multimedia. 25:50-61
- Publication Year :
- 2023
- Publisher :
- Institute of Electrical and Electronics Engineers (IEEE), 2023.
-
Abstract
- Recent transformer-based models, especially patch-based methods, have shown huge potentiality in vision tasks. However, the split fixed-size patches divide the input features into the same size patches, which ignores the fact that vision elements are often various and thus may destroy the semantic information. Also, the vanilla patch-based transformer cannot guarantee the information communication between patches, which will prevent the extraction of attention information with a global view. To circumvent those problems, we propose the Efficient Attention Pyramid Transformer (EAPT) in this paper. More specifically, we first propose Deformable Attention, which learns an offset for each position in patches. Therefore, even with split fixed-size patches, our method can still obtain non-fixed attention information that can cover various vision elements. Then, we design the Encode-Decode Communication module (En-DeC module), which can obtain communication information between all patches to get more complete global attention information. Finally, we also proposed a position encoding specifically for vision transformers, which can be used for patches of any dimensions and any lengths. Extensive experiments on the vision tasks of image classification, object detection, semantic segmentation demonstrate the effectiveness of our proposed model. Furthermore, we also conduct rigorous ablation studies to evaluate the key components of the proposed structure.
- Subjects :
- Offset (computer science)
Contextual image classification
Computer science
business.industry
ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION
Image processing
Object detection
Computer Science Applications
Encoding (memory)
Signal Processing
Media Technology
Computer vision
Segmentation
Pyramid (image processing)
Artificial intelligence
Electrical and Electronic Engineering
business
Transformer (machine learning model)
Subjects
Details
- ISSN :
- 19410077 and 15209210
- Volume :
- 25
- Database :
- OpenAIRE
- Journal :
- IEEE Transactions on Multimedia
- Accession number :
- edsair.doi...........c9c2d38362ff572c0340623892cf99d9