So sánh phương pháp

	Mô hình Khuếch tán Tiềm ẩn	Mô hình Phân đoạn Mọi thứ
Lĩnh vực	Học sâu	Học sâu
Họ	Machine learning	Machine learning
Năm ra đời	2022	2023
Người khởi xướng	Robin Rombach	Alexander Kirillov
Loại	Neural network architecture	Neural network architecture
Công trình gốc	Rombach, R., Blattmann, A., Lorenz, D., Esser, P., & Ommer, B. (2022). High-resolution image synthesis with latent diffusion models. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 10684-10695).	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).
Tên gọi khác	LDM, Stable Diffusion, Latent Diffusion	SAM, Segment Anything
Liên quan	4	4
Tóm tắt	Latent Diffusion Models (LDMs) are a generative approach introduced by Rombach et al. in 2022 that performs the diffusion process in a compressed latent space rather than pixel space, enabling efficient high-resolution image synthesis. By compressing images into a low-dimensional latent representation using a variational autoencoder, diffusion becomes computationally tractable while maintaining visual quality.	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.