So sánh phương pháp

	Mô hình Phân đoạn Mọi thứ	DETR (Detection Transformer)	Mô hình Tự mã hóa Che giấu
Lĩnh vực	Học sâu	Học sâu	Học sâu
Họ	Machine learning	Machine learning	Machine learning
Năm ra đời	2023	2020	2021
Người khởi xướng	Alexander Kirillov	Nicolas Carion	Kaiming He
Loại	Neural network architecture	Neural network architecture	Neural network architecture
Công trình gốc	Kirillov, A., Mintun, E., Darrell, T., & Girshick, R. (2023). Segment Anything. In Proceedings of the IEEE/CVF International Conference on Computer Vision (pp. 4015-4026).	Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., & Zagoruyko, S. (2020). End-to-end object detection with transformers. In European Conference on Computer Vision (pp. 213-229). Springer, Cham.	He, K., Chen, X., Xie, S., Li, Y., Dollár, P., & Girshick, R. (2022). Masked autoencoders are scalable vision learners. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 16000-16009).
Tên gọi khác	SAM, Segment Anything	Detection Transformer, DETR	MAE, Vision MAE
Liên quan	4	4	4
Tóm tắt	Segment Anything Model (SAM) is a foundation model introduced by Kirillov et al. in 2023 that can segment any object in an image given various forms of prompts. SAM is trained on a massive dataset of diverse images and learns to segment objects based on minimal user input such as points, boxes, or text descriptions.	DETR (Detection Transformer) is an end-to-end framework for object detection introduced by Carion et al. in 2020 that reformulates detection as a direct set prediction problem using transformers. Unlike traditional approaches that use hand-crafted post-processing like non-maximum suppression, DETR treats object detection as a sequence-to-sequence problem where the transformer predicts all objects at once.	Masked Autoencoders (MAE) is a self-supervised learning approach introduced by He et al. in 2021 that masks random patches of an image and trains a model to reconstruct the missing content. Adapting the masked language modeling paradigm from NLP to vision, MAE learns rich visual representations by solving a challenging reconstruction task without requiring labels.