Update object detection with latest resize and pad strategies

[qubvel]

What does this PR do?

Updates object detection example and guide. It is now possible to use image_processor's resize and pad (#30742) instead of manual padding with albumentations. Despite image_processor resize being slower than albumenations I did not observe any degradation in training speed. Of course, it depends on data and hardware environment, but probably not too critical for not-so-fast detection models where bottleneck is GPU computations.

Before submitting

• This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
• Did you read the contributor guideline,
  Pull Request section?
• Did you make sure to update the documentation with your changes? Here are the
  documentation guidelines, and
  here are tips on formatting docstrings.

Who can review?

@amyeroberts

[HuggingFaceDocBuilderDev]

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.

[amyeroberts]

Thanks for updating and running some speed tests!