Machine learningDeep Learning, Object Detection
DETR（检测变换器）
DETR（检测变换器）是由 Carion 等人在 2020 年提出的一种端到端的物体检测框架，它将检测重新表述为使用变换器（transformer）的直接集合预测问题。与使用非极大值抑制等手工后处理方法的传统方法不同，DETR 将物体检测视为一个序列到序列的问题，变换器一次性预测所有物体。
阅读完整方法
仅限会员
登录使用免费账户登录即可阅读本节。
Method map
The neighbourhood of related methods — select a node to explore.
来源
- 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. DOI: 10.1007/978-3-030-58452-8_13 ↗
如何引用本页
ScholarGate. (2026, June 3). End-to-End Object Detection with Transformers. ScholarGate. https://scholargate.app/zh/deep-learning/detr
Which method?
Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.
- 掩码自编码器深度学习↔ compare
- Segment Anything Model深度学习↔ compare
- Swin Transformer深度学习↔ compare
- 视觉曼巴深度学习↔ compare