# How does the training of a object detection dataset happen, with segmentation datasets, and how are the transformation handled **URL:** \ **Category:** YOLO\ **Tags:** question, code\ **Created:** [August 15, 2025, 10:18am UTC](https://community.ultralytics.com/t/how-does-the-training-of-a-object-detection-dataset-happen-with-segmentation-datasets-and-how-are-the-transformation-handled/1351 "2025-08-15T10:18:48Z")\ **Posts on this page:** 7\ **Page:** 1
**Author:** ![Kallinteris-Andreas](https://sea1.discourse-cdn.com/flex001/user_avatar/community.ultralytics.com/kallinteris-andreas/32/838_2.png) [@Kallinteris-Andreas](https://community.ultralytics.com/u/Kallinteris-Andreas)\ **Post date:** [August 15, 2025, 10:18am UTC](https://community.ultralytics.com/t/how-does-the-training-of-a-object-detection-dataset-happen-with-segmentation-datasets-and-how-are-the-transformation-handled/1351/1 "2025-08-15T10:18:48Z")
In Ultralytics HUB the [COCO dataset](https://docs.ultralytics.com/datasets/detect/coco/) includes segmentation polygons, not bounding boxes, but it can be used to train object detection dataset 1. are the polygon masks simply converted to bounding boxes during training 2. how are the Spatial Transforms `Albumentations` handled such as arbitrary rotations handled, is the bounding box used for training based on post transformer segmentation mask? ---
**Author:** ![Toxite](https://sea1.discourse-cdn.com/flex001/user_avatar/community.ultralytics.com/toxite/32/123_2.png) [@Toxite](https://community.ultralytics.com/u/Toxite)\ **Post date:** [August 15, 2025, 10:56pm UTC](https://community.ultralytics.com/t/how-does-the-training-of-a-object-detection-dataset-happen-with-segmentation-datasets-and-how-are-the-transformation-handled/1351/2 "2025-08-15T22:56:37Z")
1. They are converted to bounding boxes 2. Ultralytics’ native affine transform augmentations are performed using polygons if using segmentation dataset for object detection: [ultralytics/ultralytics/data/augment.py at 23d79250e7420945792362f07b8d818320fdce49 · ultralytics/ultralytics · GitHub](https://github.com/ultralytics/ultralytics/blob/23d79250e7420945792362f07b8d818320fdce49/ultralytics/data/augment.py#L1057-L1061) But `Albumentations` uses bounding boxes. It doesn’t support polygons. ---
**Author:** ![Kallinteris-Andreas](https://sea1.discourse-cdn.com/flex001/user_avatar/community.ultralytics.com/kallinteris-andreas/32/838_2.png) [@Kallinteris-Andreas](https://community.ultralytics.com/u/Kallinteris-Andreas)\ **Post date:** [August 18, 2025, 10:06am UTC](https://community.ultralytics.com/t/how-does-the-training-of-a-object-detection-dataset-happen-with-segmentation-datasets-and-how-are-the-transformation-handled/1351/3 "2025-08-18T10:06:43Z")
If Ultralytics’ affine transform is used on a dataset that contains segmentation masks, which is used to train an object detection model, is the conversion from segmentation masks to bounding boxes happening (1) before the affine transform, (2) after the affine transform This is relevant because it is (2) then the bounding box could potentially be more accurate note: btw `Albumentations` does support masks [Targets by Transform](https://albumentations.ai/docs/reference/supported-targets-by-transform/), though I think it is on dense masks, not polygon masks Thanks! ---
**Author:** ![BurhanQ](https://sea1.discourse-cdn.com/flex001/user_avatar/community.ultralytics.com/burhanq/32/7_2.png) [@BurhanQ](https://community.ultralytics.com/u/BurhanQ)\ **Post date:** [August 18, 2025, 10:52am UTC](https://community.ultralytics.com/t/how-does-the-training-of-a-object-detection-dataset-happen-with-segmentation-datasets-and-how-are-the-transformation-handled/1351/4 "2025-08-18T10:52:43Z")
> [@Kallinteris-Andreas](#): > > on a dataset that contains segmentation masks, which is used to train an object detection model Just to help clarify (because I’m confused), are you asking about using segmentation annotations to train a standard “detect” (bounding boxes) model? I presume you’re asking about using segmentation annotations to train a segmentation model, but I want to be 100% certain in my understanding. ---
**Author:** ![Kallinteris-Andreas](https://sea1.discourse-cdn.com/flex001/user_avatar/community.ultralytics.com/kallinteris-andreas/32/838_2.png) [@Kallinteris-Andreas](https://community.ultralytics.com/u/Kallinteris-Andreas)\ **Post date:** [August 18, 2025, 11:04am UTC](https://community.ultralytics.com/t/how-does-the-training-of-a-object-detection-dataset-happen-with-segmentation-datasets-and-how-are-the-transformation-handled/1351/5 "2025-08-18T11:04:32Z")
I am asking about training an object detection model with segmentation annotations ---
**Author:** ![BurhanQ](https://sea1.discourse-cdn.com/flex001/user_avatar/community.ultralytics.com/burhanq/32/7_2.png) [@BurhanQ](https://community.ultralytics.com/u/BurhanQ)\ **Post date:** [August 18, 2025, 12:01pm UTC](https://community.ultralytics.com/t/how-does-the-training-of-a-object-detection-dataset-happen-with-segmentation-datasets-and-how-are-the-transformation-handled/1351/6 "2025-08-18T12:01:18Z")
See the code here: > ---
**Author:** ![Toxite](https://sea1.discourse-cdn.com/flex001/user_avatar/community.ultralytics.com/toxite/32/123_2.png) [@Toxite](https://community.ultralytics.com/u/Toxite)\ **Post date:** [August 18, 2025, 12:18pm UTC](https://community.ultralytics.com/t/how-does-the-training-of-a-object-detection-dataset-happen-with-segmentation-datasets-and-how-are-the-transformation-handled/1351/7 "2025-08-18T12:18:31Z")
> [@Kallinteris-Andreas](#): > > If Ultralytics’ affine transform is used on a dataset that contains segmentation masks, which is used to train an object detection model, is the conversion from segmentation masks to bounding boxes happening (1) before the affine transform, (2) after the affine transform After the affine transform. And it’s like that to get accurate boxes like you mentioned.