DiagSWin: A multi-scale vision transformer with diagonal-shaped windows for object detection and segmentation
Ke Li, Di Wang, Gang Liu, Wenxuan Zhu, Haodi Zhong, Quan Wang
Topics & Concepts
Computer scienceSegmentationArtificial intelligenceTransformerComputationGranularityRendering (computer graphics)Computer visionPattern recognition (psychology)AlgorithmPhysicsOperating systemQuantum mechanicsVoltageAdvanced Neural Network ApplicationsVisual Attention and Saliency DetectionDomain Adaptation and Few-Shot Learning