Improve inst seg perf

[vinnamkim]

Summary

• Ticket no. 128949
• Stack images as possible for all tasks
• Pad images during instance segmentation data pipeline as possible
• Add non_blocking option to instance segmentation data preprocessors

How to test

Median train iter time for this command

otx train --data_root /home/vinnamki/dataset/instance_seg/coco_car_person_medium --config src/otx/recipe/instance_segmentation/maskrcnn_efficientnetb2b.yaml 

Before	After
0.247	0.236

Checklist

• [ ] I have added unit tests to cover my changes.​
• [ ] I have added integration tests to cover my changes.​
• [ ] I have added e2e tests for validation.
• [ ] I have added the description of my changes into CHANGELOG in my target branch (e.g., CHANGELOG in develop).​
• [ ] I have updated the documentation in my target branch accordingly (e.g., documentation in develop).
• [ ] I have linked related issues.

License

• [ ] I submit my code changes under the same Apache License that covers the project. Feel free to contact the maintainers if that's a concern.
• [ ] I have updated the license header for each file (see an example below).

# Copyright (C) 2023 Intel Corporation
# SPDX-License-Identifier: Apache-2.0