Local-/ Global- Feature

1) Dataset:

2) Papers:

Paper List:

Global Context:

• AttaNet: Attention-Augmented Network for Fast and Accurate Scene Parsing [Paper] [Personal Summary]

• Video Contrastive Learning with Global Context_2021 [Paper] [Personal Summary]

Local Context:

• [HaloNets] Scaling Local Self-Attention for Parameter Efficient Visual Backbones_CVPR_2021 [Paper] [Personal Summary]

• Unifying Nonlocal Blocks for Neural Networks_2021 [Paper] [Code]

• Conformer: Local Features Coupling Global Representations for Visual Recognition [Paper]

Local + Global Context:

• [LG-Transformer] Local-to-Global Self-Attention in Vision Transformers_2021 [Paper] [Personal Summary]

• Focal Self-attention for Local-Global Interactions in Vision Transformers_2021 [Paper]

• DANet: Dual Attention Network for Scene Segmentation [Paper] [Code]

• Shallow Feature Based Dense Attention Network for Crowd Counting [Paper]

• Focal Self-attention for Local-Global Interactions in Vision Transformers [Paper]

• ISNet: Integrate Image-Level and Semantic-Level Context for Semantic Segmentation

(as in DELG)

Global Feature:

• s

To-do List:

Unfilter:

References: