# \#deep-learning

**URL:** https://community.ultralytics.com/tag/deep-learning/34.md

[Latest](https://community.ultralytics.com/latest.md) · [Categories](https://community.ultralytics.com/categories.md) · [Tags](https://community.ultralytics.com/tags.md)

---

## [Standard Naming Conventions for Backbone, Neck, and Head in Object Detection Architectures?](https://community.ultralytics.com/t/standard-naming-conventions-for-backbone-neck-and-head-in-object-detection-architectures/1685)

<div class="topic-metadata">

**Author:** [@ninicom](https://community.ultralytics.com/u/ninicom)\
**Replies:** 2\
**Last updated:** [December 5, 2025, 2:37am UTC](https://community.ultralytics.com/t/standard-naming-conventions-for-backbone-neck-and-head-in-object-detection-architectures/1685 "2025-12-05T02:37:33Z")

</div>

In the architecture diagram I am reproducing, I have temporarily denoted the Backbone blocks as B, the Neck components as T, and the inputs to the Head as U. I realize this notation is likely non-standard. Could you r…