Part 5: Modern Computer Vision
No matching items
jshn9515
2026-05-05
2026-07-06
| Title | Author | Date |
|---|---|---|
| 11.1 From CNN to Vision Transformer: Treating Images as Sequences | jshn9515 | 2026-05-11 |
| 11.2 Patch Embedding: Cutting Images into Tokens | jshn9515 | 2026-05-12 |
| 11.3 Class Token and Positional Embedding: Letting a Sequence Represent the Whole Image | jshn9515 | 2026-05-13 |
| 11.4 ViT Encoder: Letting Patch Tokens Exchange Information | jshn9515 | 2026-05-13 |
| 11.5 ViT Backbone: Pretraining and Fine-Tuning | jshn9515 | 2026-05-19 |