DilateFormer: Multi-Scale Dilated Transformer for Visual Recognition.
Jiayu JiaoYu-Ming TangKun-Yu LinYipeng GaoAndy J. MaYaowei WangWei-Shi ZhengPublished in: IEEE Trans. Multim. (2023)
Keyphrases
- visual recognition
- multiscale
- image classification
- visual recognition tasks
- fuzzy logic
- image representation
- scale space
- image processing
- object recognition
- image segmentation
- edge detection
- fault diagnosis
- latent topic models
- view independent
- grey level
- natural images
- visual categorization
- coarse to fine
- machine learning
- scene classification
- visual classification
- user interface
- category level
- feature selection