방법 비교
선택한 방법을 나란히 검토하세요. 서로 다른 행은 강조 표시됩니다.
| 도메인 적응형 합성곱 신경망× | 도메인 적응형 비전 트랜스포머× | |
|---|---|---|
| 분야 | 딥러닝 | 딥러닝 |
| 계열 | Machine learning | Machine learning |
| 기원 연도≠ | 2015–2017 | 2021–2023 |
| 창시자≠ | Ganin, Y. & Lempitsky, V. (domain-adversarial framework); Tzeng et al. (ADDA) | Multiple groups (Yang et al., 2023; Xu et al., 2021; Ma et al., 2022) |
| 유형≠ | Domain-adaptive deep learning model | Domain adaptation + Vision Transformer ensemble |
| 원전≠ | Ganin, Y., Ustinova, E., Ajakan, H., Germain, P., Larochelle, H., Laviolette, F., Marchand, M., & Lempitsky, V. (2016). Domain-adversarial training of neural networks. Journal of Machine Learning Research, 17(59), 1–35. link ↗ | Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., ... & Houlsby, N. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. International Conference on Learning Representations (ICLR). link ↗ |
| 별칭 | DA-CNN, domain adaptation CNN, domain-adaptive deep convolutional network, CNN with domain adaptation | DA-ViT, Domain Adaptation with Vision Transformer, ViT with Domain Adaptation, Domain-Adaptive ViT |
| 관련 | 5 | 5 |
| 요약≠ | A domain-adaptive CNN trains a convolutional network on a labeled source domain and adapts its learned feature representations to an unlabeled or lightly labeled target domain, bridging the distribution gap so that visual classifiers transfer reliably across datasets, sensors, or imaging conditions without full re-annotation. | Domain-Adaptive Vision Transformer (DA-ViT) applies domain adaptation techniques — such as adversarial alignment, self-training, or attention-level bridging — on top of a pretrained Vision Transformer backbone to transfer visual knowledge from a labeled source domain to an unlabeled or lightly labeled target domain, reducing the distribution shift that limits standard ViT fine-tuning. |
| ScholarGate데이터셋 ↗ |
|
|