SlideShare une entreprise Scribd logo
1  sur  9
Télécharger pour lire hors ligne
Paper review:
2023.01.19
Uploaded on ArXiv: April 2022
Background
• For Transformer models global context modelling capabilities, the computational complexity
grows quadratically.
• It limits their ability to scale up to high-resolution scenarios.
• Local attention on spatially local windows benefit for linear complexity, but with a loss of global
contextual information.
• It is important to design an architecture that can capture global contexts while maintaining
efficiency.
Introduction
• Effective vision transformer architecture that can capture global context while maintaining
computational efficiency.
• Exploits self-attention mechanisms with both “spatial tokens” and “channel tokens”.
• With spatial tokens, the spatial dimension defines the token scope, and the channel dimension defines the token feature
dimension.
• With channel tokens, it is inversed: the channel dimension defines the token scope, and the spatial dimension defines the
token feature dimension.
• Tokens along the sequence direction are further grouped for both spatial and channel tokens to maintain the linear
complexity of the entire model.
• These two self-attentions complement each other.
• Since each channel token contains an abstract representation of the entire image -> the channel attention naturally captures
global interactions and representations by taking all spatial positions into account when computing attention scores between
channels.
• The spatial attention refines the local representations by performing fine-grained interactions across spatial locations, which
in turn helps the global information modeling in channel attention.
• DaViT achieved state-of-the-art performance on four different tasks with efficient computations.
Spatial and Channel Dual Attention
Attention
• Standard global self-attention
• Complexity of O(2P2C + 4PC2)
• Spatial window-based self-attention
• Complexity of O(2PPwC+4PC2)
• Linear complexity with spatial size P
• Channel Group Attention
• Complexity of O(6PC2)
• Linear complexity with spatial size P
Nw: Number of windows, Ng: Number of channel group, Cg: Channels per group, Ch: Channels per head
Dual Attention Block Architecture
Comparisons of efficiency vs. performance
Results – Image Classification
and Semantic Segmentation
Results – Object Detection

Contenu connexe

Similaire à DaViT.pdf

Performance Analysis of Lattice QCD with APGAS Programming Model
Performance Analysis of Lattice QCD with APGAS Programming ModelPerformance Analysis of Lattice QCD with APGAS Programming Model
Performance Analysis of Lattice QCD with APGAS Programming ModelKoichi Shirahata
 
Transformer Mods for Document Length Inputs
Transformer Mods for Document Length InputsTransformer Mods for Document Length Inputs
Transformer Mods for Document Length InputsSujit Pal
 
240226_Thanh_LabSeminar[Structure-Aware Transformer for Graph Representation ...
240226_Thanh_LabSeminar[Structure-Aware Transformer for Graph Representation ...240226_Thanh_LabSeminar[Structure-Aware Transformer for Graph Representation ...
240226_Thanh_LabSeminar[Structure-Aware Transformer for Graph Representation ...thanhdowork
 
240226_Thanh_LabSeminar[Structure-Aware Transformer for Graph Representation ...
240226_Thanh_LabSeminar[Structure-Aware Transformer for Graph Representation ...240226_Thanh_LabSeminar[Structure-Aware Transformer for Graph Representation ...
240226_Thanh_LabSeminar[Structure-Aware Transformer for Graph Representation ...thanhdowork
 
Survey of Attention mechanism & Use in Computer Vision
Survey of Attention mechanism & Use in Computer VisionSurvey of Attention mechanism & Use in Computer Vision
Survey of Attention mechanism & Use in Computer VisionSwatiNarkhede1
 
240429_Thuy_Labseminar[Simplifying and Empowering Transformers for Large-Grap...
240429_Thuy_Labseminar[Simplifying and Empowering Transformers for Large-Grap...240429_Thuy_Labseminar[Simplifying and Empowering Transformers for Large-Grap...
240429_Thuy_Labseminar[Simplifying and Empowering Transformers for Large-Grap...thanhdowork
 
Deep learning for 3-D Scene Reconstruction and Modeling
Deep learning for 3-D Scene Reconstruction and Modeling Deep learning for 3-D Scene Reconstruction and Modeling
Deep learning for 3-D Scene Reconstruction and Modeling Yu Huang
 
Convolutional Neural Networks : Popular Architectures
Convolutional Neural Networks : Popular ArchitecturesConvolutional Neural Networks : Popular Architectures
Convolutional Neural Networks : Popular Architecturesananth
 
ConvNeXt: A ConvNet for the 2020s explained
ConvNeXt: A ConvNet for the 2020s explainedConvNeXt: A ConvNet for the 2020s explained
ConvNeXt: A ConvNet for the 2020s explainedSushant Gautam
 
“How Transformers are Changing the Direction of Deep Learning Architectures,”...
“How Transformers are Changing the Direction of Deep Learning Architectures,”...“How Transformers are Changing the Direction of Deep Learning Architectures,”...
“How Transformers are Changing the Direction of Deep Learning Architectures,”...Edge AI and Vision Alliance
 
Presentation vision transformersppt.pptx
Presentation vision transformersppt.pptxPresentation vision transformersppt.pptx
Presentation vision transformersppt.pptxhtn540
 
PR-108: MobileNetV2: Inverted Residuals and Linear Bottlenecks
PR-108: MobileNetV2: Inverted Residuals and Linear BottlenecksPR-108: MobileNetV2: Inverted Residuals and Linear Bottlenecks
PR-108: MobileNetV2: Inverted Residuals and Linear BottlenecksJinwon Lee
 
final_project_1_2k21cse07.pptx
final_project_1_2k21cse07.pptxfinal_project_1_2k21cse07.pptx
final_project_1_2k21cse07.pptxshwetabhagat25
 
PR243: Designing Network Design Spaces
PR243: Designing Network Design SpacesPR243: Designing Network Design Spaces
PR243: Designing Network Design SpacesJinwon Lee
 
Moldable pipelines for CNNs on heterogeneous edge devices
Moldable pipelines for CNNs on heterogeneous edge devicesMoldable pipelines for CNNs on heterogeneous edge devices
Moldable pipelines for CNNs on heterogeneous edge devicesLEGATO project
 
Faster R-CNN - PR012
Faster R-CNN - PR012Faster R-CNN - PR012
Faster R-CNN - PR012Jinwon Lee
 
Week5-Faster R-CNN.pptx
Week5-Faster R-CNN.pptxWeek5-Faster R-CNN.pptx
Week5-Faster R-CNN.pptxfahmi324663
 
Lecture 2.B: Computer Vision Applications - Full Stack Deep Learning - Spring...
Lecture 2.B: Computer Vision Applications - Full Stack Deep Learning - Spring...Lecture 2.B: Computer Vision Applications - Full Stack Deep Learning - Spring...
Lecture 2.B: Computer Vision Applications - Full Stack Deep Learning - Spring...Sergey Karayev
 
Fisheye Omnidirectional View in Autonomous Driving
Fisheye Omnidirectional View in Autonomous DrivingFisheye Omnidirectional View in Autonomous Driving
Fisheye Omnidirectional View in Autonomous DrivingYu Huang
 

Similaire à DaViT.pdf (20)

Performance Analysis of Lattice QCD with APGAS Programming Model
Performance Analysis of Lattice QCD with APGAS Programming ModelPerformance Analysis of Lattice QCD with APGAS Programming Model
Performance Analysis of Lattice QCD with APGAS Programming Model
 
Transformer Mods for Document Length Inputs
Transformer Mods for Document Length InputsTransformer Mods for Document Length Inputs
Transformer Mods for Document Length Inputs
 
240226_Thanh_LabSeminar[Structure-Aware Transformer for Graph Representation ...
240226_Thanh_LabSeminar[Structure-Aware Transformer for Graph Representation ...240226_Thanh_LabSeminar[Structure-Aware Transformer for Graph Representation ...
240226_Thanh_LabSeminar[Structure-Aware Transformer for Graph Representation ...
 
240226_Thanh_LabSeminar[Structure-Aware Transformer for Graph Representation ...
240226_Thanh_LabSeminar[Structure-Aware Transformer for Graph Representation ...240226_Thanh_LabSeminar[Structure-Aware Transformer for Graph Representation ...
240226_Thanh_LabSeminar[Structure-Aware Transformer for Graph Representation ...
 
Survey of Attention mechanism & Use in Computer Vision
Survey of Attention mechanism & Use in Computer VisionSurvey of Attention mechanism & Use in Computer Vision
Survey of Attention mechanism & Use in Computer Vision
 
240429_Thuy_Labseminar[Simplifying and Empowering Transformers for Large-Grap...
240429_Thuy_Labseminar[Simplifying and Empowering Transformers for Large-Grap...240429_Thuy_Labseminar[Simplifying and Empowering Transformers for Large-Grap...
240429_Thuy_Labseminar[Simplifying and Empowering Transformers for Large-Grap...
 
Deep learning for 3-D Scene Reconstruction and Modeling
Deep learning for 3-D Scene Reconstruction and Modeling Deep learning for 3-D Scene Reconstruction and Modeling
Deep learning for 3-D Scene Reconstruction and Modeling
 
Convolutional Neural Networks : Popular Architectures
Convolutional Neural Networks : Popular ArchitecturesConvolutional Neural Networks : Popular Architectures
Convolutional Neural Networks : Popular Architectures
 
ConvNeXt: A ConvNet for the 2020s explained
ConvNeXt: A ConvNet for the 2020s explainedConvNeXt: A ConvNet for the 2020s explained
ConvNeXt: A ConvNet for the 2020s explained
 
“How Transformers are Changing the Direction of Deep Learning Architectures,”...
“How Transformers are Changing the Direction of Deep Learning Architectures,”...“How Transformers are Changing the Direction of Deep Learning Architectures,”...
“How Transformers are Changing the Direction of Deep Learning Architectures,”...
 
Presentation vision transformersppt.pptx
Presentation vision transformersppt.pptxPresentation vision transformersppt.pptx
Presentation vision transformersppt.pptx
 
PR-108: MobileNetV2: Inverted Residuals and Linear Bottlenecks
PR-108: MobileNetV2: Inverted Residuals and Linear BottlenecksPR-108: MobileNetV2: Inverted Residuals and Linear Bottlenecks
PR-108: MobileNetV2: Inverted Residuals and Linear Bottlenecks
 
final_project_1_2k21cse07.pptx
final_project_1_2k21cse07.pptxfinal_project_1_2k21cse07.pptx
final_project_1_2k21cse07.pptx
 
PR243: Designing Network Design Spaces
PR243: Designing Network Design SpacesPR243: Designing Network Design Spaces
PR243: Designing Network Design Spaces
 
Moldable pipelines for CNNs on heterogeneous edge devices
Moldable pipelines for CNNs on heterogeneous edge devicesMoldable pipelines for CNNs on heterogeneous edge devices
Moldable pipelines for CNNs on heterogeneous edge devices
 
Faster R-CNN - PR012
Faster R-CNN - PR012Faster R-CNN - PR012
Faster R-CNN - PR012
 
Week5-Faster R-CNN.pptx
Week5-Faster R-CNN.pptxWeek5-Faster R-CNN.pptx
Week5-Faster R-CNN.pptx
 
Andrea Sini Thesis
Andrea Sini ThesisAndrea Sini Thesis
Andrea Sini Thesis
 
Lecture 2.B: Computer Vision Applications - Full Stack Deep Learning - Spring...
Lecture 2.B: Computer Vision Applications - Full Stack Deep Learning - Spring...Lecture 2.B: Computer Vision Applications - Full Stack Deep Learning - Spring...
Lecture 2.B: Computer Vision Applications - Full Stack Deep Learning - Spring...
 
Fisheye Omnidirectional View in Autonomous Driving
Fisheye Omnidirectional View in Autonomous DrivingFisheye Omnidirectional View in Autonomous Driving
Fisheye Omnidirectional View in Autonomous Driving
 

Dernier

Design For Accessibility: Getting it right from the start
Design For Accessibility: Getting it right from the startDesign For Accessibility: Getting it right from the start
Design For Accessibility: Getting it right from the startQuintin Balsdon
 
Thermal Engineering Unit - I & II . ppt
Thermal Engineering  Unit - I & II . pptThermal Engineering  Unit - I & II . ppt
Thermal Engineering Unit - I & II . pptDineshKumar4165
 
VIP Call Girls Ankleshwar 7001035870 Whatsapp Number, 24/07 Booking
VIP Call Girls Ankleshwar 7001035870 Whatsapp Number, 24/07 BookingVIP Call Girls Ankleshwar 7001035870 Whatsapp Number, 24/07 Booking
VIP Call Girls Ankleshwar 7001035870 Whatsapp Number, 24/07 Bookingdharasingh5698
 
Minimum and Maximum Modes of microprocessor 8086
Minimum and Maximum Modes of microprocessor 8086Minimum and Maximum Modes of microprocessor 8086
Minimum and Maximum Modes of microprocessor 8086anil_gaur
 
VIP Call Girls Palanpur 7001035870 Whatsapp Number, 24/07 Booking
VIP Call Girls Palanpur 7001035870 Whatsapp Number, 24/07 BookingVIP Call Girls Palanpur 7001035870 Whatsapp Number, 24/07 Booking
VIP Call Girls Palanpur 7001035870 Whatsapp Number, 24/07 Bookingdharasingh5698
 
Employee leave management system project.
Employee leave management system project.Employee leave management system project.
Employee leave management system project.Kamal Acharya
 
Unit 2- Effective stress & Permeability.pdf
Unit 2- Effective stress & Permeability.pdfUnit 2- Effective stress & Permeability.pdf
Unit 2- Effective stress & Permeability.pdfRagavanV2
 
UNIT - IV - Air Compressors and its Performance
UNIT - IV - Air Compressors and its PerformanceUNIT - IV - Air Compressors and its Performance
UNIT - IV - Air Compressors and its Performancesivaprakash250
 
University management System project report..pdf
University management System project report..pdfUniversity management System project report..pdf
University management System project report..pdfKamal Acharya
 
Top Rated Call Girls In chittoor 📱 {7001035870} VIP Escorts chittoor
Top Rated Call Girls In chittoor 📱 {7001035870} VIP Escorts chittoorTop Rated Call Girls In chittoor 📱 {7001035870} VIP Escorts chittoor
Top Rated Call Girls In chittoor 📱 {7001035870} VIP Escorts chittoordharasingh5698
 
data_management_and _data_science_cheat_sheet.pdf
data_management_and _data_science_cheat_sheet.pdfdata_management_and _data_science_cheat_sheet.pdf
data_management_and _data_science_cheat_sheet.pdfJiananWang21
 
Generative AI or GenAI technology based PPT
Generative AI or GenAI technology based PPTGenerative AI or GenAI technology based PPT
Generative AI or GenAI technology based PPTbhaskargani46
 
Standard vs Custom Battery Packs - Decoding the Power Play
Standard vs Custom Battery Packs - Decoding the Power PlayStandard vs Custom Battery Packs - Decoding the Power Play
Standard vs Custom Battery Packs - Decoding the Power PlayEpec Engineered Technologies
 
COST-EFFETIVE and Energy Efficient BUILDINGS ptx
COST-EFFETIVE  and Energy Efficient BUILDINGS ptxCOST-EFFETIVE  and Energy Efficient BUILDINGS ptx
COST-EFFETIVE and Energy Efficient BUILDINGS ptxJIT KUMAR GUPTA
 
Call Girls In Bangalore ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Bangalore ☎ 7737669865 🥵 Book Your One night StandCall Girls In Bangalore ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Bangalore ☎ 7737669865 🥵 Book Your One night Standamitlee9823
 
Work-Permit-Receiver-in-Saudi-Aramco.pptx
Work-Permit-Receiver-in-Saudi-Aramco.pptxWork-Permit-Receiver-in-Saudi-Aramco.pptx
Work-Permit-Receiver-in-Saudi-Aramco.pptxJuliansyahHarahap1
 
Navigating Complexity: The Role of Trusted Partners and VIAS3D in Dassault Sy...
Navigating Complexity: The Role of Trusted Partners and VIAS3D in Dassault Sy...Navigating Complexity: The Role of Trusted Partners and VIAS3D in Dassault Sy...
Navigating Complexity: The Role of Trusted Partners and VIAS3D in Dassault Sy...Arindam Chakraborty, Ph.D., P.E. (CA, TX)
 

Dernier (20)

Design For Accessibility: Getting it right from the start
Design For Accessibility: Getting it right from the startDesign For Accessibility: Getting it right from the start
Design For Accessibility: Getting it right from the start
 
Thermal Engineering Unit - I & II . ppt
Thermal Engineering  Unit - I & II . pptThermal Engineering  Unit - I & II . ppt
Thermal Engineering Unit - I & II . ppt
 
Call Girls in Netaji Nagar, Delhi 💯 Call Us 🔝9953056974 🔝 Escort Service
Call Girls in Netaji Nagar, Delhi 💯 Call Us 🔝9953056974 🔝 Escort ServiceCall Girls in Netaji Nagar, Delhi 💯 Call Us 🔝9953056974 🔝 Escort Service
Call Girls in Netaji Nagar, Delhi 💯 Call Us 🔝9953056974 🔝 Escort Service
 
VIP Call Girls Ankleshwar 7001035870 Whatsapp Number, 24/07 Booking
VIP Call Girls Ankleshwar 7001035870 Whatsapp Number, 24/07 BookingVIP Call Girls Ankleshwar 7001035870 Whatsapp Number, 24/07 Booking
VIP Call Girls Ankleshwar 7001035870 Whatsapp Number, 24/07 Booking
 
Minimum and Maximum Modes of microprocessor 8086
Minimum and Maximum Modes of microprocessor 8086Minimum and Maximum Modes of microprocessor 8086
Minimum and Maximum Modes of microprocessor 8086
 
VIP Call Girls Palanpur 7001035870 Whatsapp Number, 24/07 Booking
VIP Call Girls Palanpur 7001035870 Whatsapp Number, 24/07 BookingVIP Call Girls Palanpur 7001035870 Whatsapp Number, 24/07 Booking
VIP Call Girls Palanpur 7001035870 Whatsapp Number, 24/07 Booking
 
Employee leave management system project.
Employee leave management system project.Employee leave management system project.
Employee leave management system project.
 
Unit 2- Effective stress & Permeability.pdf
Unit 2- Effective stress & Permeability.pdfUnit 2- Effective stress & Permeability.pdf
Unit 2- Effective stress & Permeability.pdf
 
UNIT - IV - Air Compressors and its Performance
UNIT - IV - Air Compressors and its PerformanceUNIT - IV - Air Compressors and its Performance
UNIT - IV - Air Compressors and its Performance
 
University management System project report..pdf
University management System project report..pdfUniversity management System project report..pdf
University management System project report..pdf
 
Top Rated Call Girls In chittoor 📱 {7001035870} VIP Escorts chittoor
Top Rated Call Girls In chittoor 📱 {7001035870} VIP Escorts chittoorTop Rated Call Girls In chittoor 📱 {7001035870} VIP Escorts chittoor
Top Rated Call Girls In chittoor 📱 {7001035870} VIP Escorts chittoor
 
data_management_and _data_science_cheat_sheet.pdf
data_management_and _data_science_cheat_sheet.pdfdata_management_and _data_science_cheat_sheet.pdf
data_management_and _data_science_cheat_sheet.pdf
 
(INDIRA) Call Girl Bhosari Call Now 8617697112 Bhosari Escorts 24x7
(INDIRA) Call Girl Bhosari Call Now 8617697112 Bhosari Escorts 24x7(INDIRA) Call Girl Bhosari Call Now 8617697112 Bhosari Escorts 24x7
(INDIRA) Call Girl Bhosari Call Now 8617697112 Bhosari Escorts 24x7
 
Generative AI or GenAI technology based PPT
Generative AI or GenAI technology based PPTGenerative AI or GenAI technology based PPT
Generative AI or GenAI technology based PPT
 
Standard vs Custom Battery Packs - Decoding the Power Play
Standard vs Custom Battery Packs - Decoding the Power PlayStandard vs Custom Battery Packs - Decoding the Power Play
Standard vs Custom Battery Packs - Decoding the Power Play
 
COST-EFFETIVE and Energy Efficient BUILDINGS ptx
COST-EFFETIVE  and Energy Efficient BUILDINGS ptxCOST-EFFETIVE  and Energy Efficient BUILDINGS ptx
COST-EFFETIVE and Energy Efficient BUILDINGS ptx
 
Cara Menggugurkan Sperma Yang Masuk Rahim Biyar Tidak Hamil
Cara Menggugurkan Sperma Yang Masuk Rahim Biyar Tidak HamilCara Menggugurkan Sperma Yang Masuk Rahim Biyar Tidak Hamil
Cara Menggugurkan Sperma Yang Masuk Rahim Biyar Tidak Hamil
 
Call Girls In Bangalore ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Bangalore ☎ 7737669865 🥵 Book Your One night StandCall Girls In Bangalore ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Bangalore ☎ 7737669865 🥵 Book Your One night Stand
 
Work-Permit-Receiver-in-Saudi-Aramco.pptx
Work-Permit-Receiver-in-Saudi-Aramco.pptxWork-Permit-Receiver-in-Saudi-Aramco.pptx
Work-Permit-Receiver-in-Saudi-Aramco.pptx
 
Navigating Complexity: The Role of Trusted Partners and VIAS3D in Dassault Sy...
Navigating Complexity: The Role of Trusted Partners and VIAS3D in Dassault Sy...Navigating Complexity: The Role of Trusted Partners and VIAS3D in Dassault Sy...
Navigating Complexity: The Role of Trusted Partners and VIAS3D in Dassault Sy...
 

DaViT.pdf

  • 2. Background • For Transformer models global context modelling capabilities, the computational complexity grows quadratically. • It limits their ability to scale up to high-resolution scenarios. • Local attention on spatially local windows benefit for linear complexity, but with a loss of global contextual information. • It is important to design an architecture that can capture global contexts while maintaining efficiency.
  • 3. Introduction • Effective vision transformer architecture that can capture global context while maintaining computational efficiency. • Exploits self-attention mechanisms with both “spatial tokens” and “channel tokens”. • With spatial tokens, the spatial dimension defines the token scope, and the channel dimension defines the token feature dimension. • With channel tokens, it is inversed: the channel dimension defines the token scope, and the spatial dimension defines the token feature dimension. • Tokens along the sequence direction are further grouped for both spatial and channel tokens to maintain the linear complexity of the entire model. • These two self-attentions complement each other. • Since each channel token contains an abstract representation of the entire image -> the channel attention naturally captures global interactions and representations by taking all spatial positions into account when computing attention scores between channels. • The spatial attention refines the local representations by performing fine-grained interactions across spatial locations, which in turn helps the global information modeling in channel attention. • DaViT achieved state-of-the-art performance on four different tasks with efficient computations.
  • 4. Spatial and Channel Dual Attention
  • 5. Attention • Standard global self-attention • Complexity of O(2P2C + 4PC2) • Spatial window-based self-attention • Complexity of O(2PPwC+4PC2) • Linear complexity with spatial size P • Channel Group Attention • Complexity of O(6PC2) • Linear complexity with spatial size P Nw: Number of windows, Ng: Number of channel group, Cg: Channels per group, Ch: Channels per head
  • 6. Dual Attention Block Architecture
  • 7. Comparisons of efficiency vs. performance
  • 8. Results – Image Classification and Semantic Segmentation
  • 9. Results – Object Detection