DilateFormer: Multi-Scale Dilated Transformer for Visual Recognition.
Jiayu JiaoYu-Ming TangKun-Yu LinYipeng GaoJinhua MaYaowei WangWei-Shi ZhengPublished in: CoRR (2023)
Keyphrases
- visual recognition
- multiscale
- image classification
- object recognition
- scale space
- natural images
- fault diagnosis
- latent topic models
- visual categorization
- edge detection
- image segmentation
- grey level
- image processing
- fuzzy logic
- image representation
- view independent
- coarse to fine
- local binary pattern
- natural scenes
- visual classification
- visual recognition tasks
- computer vision