So sánh phương pháp
Xem các phương pháp đã chọn cạnh nhau; những hàng khác biệt được làm nổi bật.
| Phân đoạn ngữ nghĩa tự giám sát× | Mạng nơ-ron tích chập tự giám sát× | |
|---|---|---|
| Lĩnh vực | Học sâu | Học sâu |
| Họ | Machine learning | Machine learning |
| Năm ra đời≠ | 2020–2022 | 2018–2020 |
| Người khởi xướng≠ | Multiple groups (Caron et al.; Hamilton et al. among key contributors) | LeCun, Y. (CNN backbone); Chen et al. and He et al. (self-supervised visual frameworks) |
| Loại≠ | Self-supervised dense prediction | Self-supervised deep learning |
| Công trình gốc≠ | Caron, M., Touvron, H., Misra, I., Jegou, H., Mairal, J., Bojanowski, P., & Joulin, A. (2021). Emerging Properties in Self-Supervised Vision Transformers. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 9650–9660. DOI ↗ | Chen, T., Kornblith, S., Norouzi, M., & Hinton, G. (2020). A Simple Framework for Contrastive Learning of Visual Representations. In Proceedings of the 37th International Conference on Machine Learning (ICML 2020), PMLR 119, 1597–1607. link ↗ |
| Tên gọi khác | SSL semantic segmentation, unsupervised semantic segmentation, label-free semantic segmentation, self-supervised dense prediction | Self-supervised CNN, SSL-CNN, contrastive CNN, pretext-task CNN |
| Liên quan | 5 | 5 |
| Tóm tắt≠ | Self-supervised semantic segmentation learns to assign a class label to every pixel of an image without relying on manually annotated segmentation masks. A backbone network is first trained on large quantities of unlabeled images using self-supervised objectives such as contrastive learning or masked image modeling, and the resulting dense features are then used to partition and label image regions, achieving competitive segmentation quality at a fraction of the annotation cost. | A self-supervised convolutional neural network (CNN) learns powerful visual representations from unlabeled images by solving pretext tasks — such as contrastive instance discrimination or masked-patch prediction — and then fine-tunes on a small labeled set. This approach dramatically reduces dependence on large annotated datasets while preserving the spatial feature-extraction strengths of convolutional architectures. |
| ScholarGateBộ dữ liệu ↗ |
|
|