CrossFormer: A Versatile Vision Transformer Based on Cross-scale Attention

72 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Transformers in Vision: A Survey (2021, methodology): “Similarly, CrossFormer [211] has a hierarchical pyramid structure, and introduces cross-scale embedding module, along-with long short distance attention and dynamic position bias to faithfully capture both local and global visual cues.”
LocalViT: Analyzing Locality in Vision Transformers (2021, unknown): “Some works already contributed towards this goal [20], [1], [34], [35], [36], [37].”
DilateFormer: Multi-Scale Dilated Transformer for Visual Recognition (2023, methodology): “[35], [41], [51], [53], [70], [93], [114] is beneficial for dense prediction tasks such as object detection, instance and semantic segmentation, recent works [21], [23], [32], [38], [42], [54], [58], [66], [77], [78], [95], [104] introduce multi-scale modeling capability by using a pyramid structure”
Multi-Scale High-Resolution Vision Transformer for Semantic Segmentation (2021, background): “Beyond classical CNNs, vision Transformers (ViTs) have emerged with competitive performance in computer vision tasks [2, 3, 5, 11, 12, 17, 19, 26, 29, 30, 33, 34, 37, 41].”