Implement XAI for tiling detection

[GalyaZalesskaya]

Summary

This PR implements the functionality to use saliency maps for tiles and merge them in the unite saliency map. The current approach is to resize a whole image and use its saliency map, which suffers from the lack of details.
The results of the new approach and the current one are below.

Also, the exact same merging mechanism was applied for Mask RCNN (Instance Segmentation) Pytorch inference:

For Mask RCNN (Instance Segmentation) OpenVINO inference saliency maps aren't returned for each tole. So, the merged masks for the united image were used.

What was added:

• Merging saliency maps functionality, using both saliency maps from tiles and a whole image, add non-linear normalization afterward

• Add implementation for PyTorch inference and OpenVINO inference for all detection models

• Add implementation to merge saliency maps for Pytorch task for Instance Segmentation task (Mask RCNN)

• Updated saliency map generation for OpenVINO inference task for Instance Segmentation

  • Changed a way to merge masks for each objects, added confidence scores to mask value
  • Moved saliency map generation process for Instance Segmentation from /model_wrappers/openvino_models.py to tiler.py implementation to keep tiled saliency map generation for OpenVINO task in one file (negotiable)

• Add parameter in BaseRecordingForwardHook whether to return normalized saliency maps

• Add parameter in DetClassProbabilityMapHook whether to use softmax in saliency maps postprocessing

• Fixed the issue there during workplace creation for Mask RCNN model deployment_tile_classifier.py config file wasn't created

• Unit tests

• e2e tests

CVS-108355

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

[eunwoosh]

Could you add and update unit test?

[eunwoosh]

Thanks for good enhancement! I left some comments. please take a look.

[jaegukhyun]

Overally LGTM, As Eunwoo said, could you add unit test to cover your PR? And is there no need to add intg or e2e test for this feature?

[negvet]

Thank you for a PR!
Could you please rebase on develop (#2227 was merged), and take a look on how it works for m-rcnn (both torch and OV tasks)? thanks!

[jaegukhyun]

Could you resolve conflicts?

[GalyaZalesskaya]

@eunwoosh @jaegukhyun @negvet @sovrasov
Sorry for the delay, I was updating my PR to cover case with Mask RCNN Instance Segmentation model and to cover latest changes in develop.
Thank you all for your valuable comments. Can you please look again?

[GalyaZalesskaya]

@negvet @sovrasov Also would like to hear your opinion about moving saliency map generation for Mask RCNN to tiler.py

[eunwoosh]

Could you check fail test cases?