Add mask-based visualization support to LLMAttributionResult.plot_image_heatmap#1757
Closed
aobo-y wants to merge 6 commits into
Closed
Add mask-based visualization support to LLMAttributionResult.plot_image_heatmap#1757aobo-y wants to merge 6 commits into
aobo-y wants to merge 6 commits into
Conversation
Contributor
Summary: add util to visualize how the image is segmented into features Differential Revision: D89953376
Summary: as title Differential Revision: D89954220
Summary: as title Reviewed By: styusuf Differential Revision: D89954477
Summary: Extract the mask list generation logic into a reusable method, centralizing the logic for creating binary masks from either mask_list or mask tensor Reviewed By: sarahtranfb Differential Revision: D90034703
…n module (meta-pytorch#1756) Summary: Extract border and legend drawing logic from `plot_mask_overlay` into reusable utility functions `draw_mask_border` and `draw_mask_legend` in the visualization Differential Revision: D90036627
…ge_heatmap (meta-pytorch#1757) Summary: Enable `plot_image_heatmap` to leverage the new `draw_mask_border` and `draw_mask_legend` utilities when the input has mask segments. This provides better visualization for image attribution with discrete regions, displaying attribution colors per segment with borders and labels derived from the salience values. Differential Revision: D90038941
aobo-y
force-pushed
the
export-D90038941
branch
from
0d4bf74 to
4c16dea
Compare
aobo-y
added a commit
to aobo-y/captum
that referenced
this pull request
Jan 2, 2026
…ge_heatmap (meta-pytorch#1757) Summary: Enable `plot_image_heatmap` to leverage the new `draw_mask_border` and `draw_mask_legend` utilities when the input has mask segments. This provides better visualization for image attribution with discrete regions, displaying attribution colors per segment with borders and labels derived from the salience values. Differential Revision: D90038941
aobo-y
added a commit
to aobo-y/captum
that referenced
this pull request
Jan 3, 2026
…ge_heatmap (meta-pytorch#1757) Summary: Enable `plot_image_heatmap` to leverage the new `draw_mask_border` and `draw_mask_legend` utilities when the input has mask segments. This provides better visualization for image attribution with discrete regions, displaying attribution colors per segment with borders and labels derived from the salience values. Differential Revision: D90038941
aobo-y
added a commit
to aobo-y/captum
that referenced
this pull request
Jan 3, 2026
…ge_heatmap (meta-pytorch#1757) Summary: Enable `plot_image_heatmap` to leverage the new `draw_mask_border` and `draw_mask_legend` utilities when the input has mask segments. This provides better visualization for image attribution with discrete regions, displaying attribution colors per segment with borders and labels derived from the salience values. Differential Revision: D90038941
aobo-y
added a commit
to aobo-y/captum
that referenced
this pull request
Jan 3, 2026
…ge_heatmap (meta-pytorch#1757) Summary: Enable `plot_image_heatmap` to leverage the new `draw_mask_border` and `draw_mask_legend` utilities when the input has mask segments. This provides better visualization for image attribution with discrete regions, displaying attribution colors per segment with borders and labels derived from the salience values. Differential Revision: D90038941
aobo-y
added a commit
to aobo-y/captum
that referenced
this pull request
Jan 3, 2026
…ge_heatmap (meta-pytorch#1757) Summary: Enable `plot_image_heatmap` to leverage the new `draw_mask_border` and `draw_mask_legend` utilities when the input has mask segments. This provides better visualization for image attribution with discrete regions, displaying attribution colors per segment with borders and labels derived from the salience values. Differential Revision: D90038941
aobo-y
added a commit
to aobo-y/captum
that referenced
this pull request
Jan 3, 2026
…ge_heatmap (meta-pytorch#1757) Summary: Enable `plot_image_heatmap` to leverage the new `draw_mask_border` and `draw_mask_legend` utilities when the input has mask segments. This provides better visualization for image attribution with discrete regions, displaying attribution colors per segment with borders and labels derived from the salience values. Differential Revision: D90038941
aobo-y
added a commit
to aobo-y/captum
that referenced
this pull request
Jan 3, 2026
…ge_heatmap (meta-pytorch#1757) Summary: Enable `plot_image_heatmap` to leverage the new `draw_mask_border` and `draw_mask_legend` utilities when the input has mask segments. This provides better visualization for image attribution with discrete regions, displaying attribution colors per segment with borders and labels derived from the salience values. Differential Revision: D90038941
aobo-y
added a commit
to aobo-y/captum
that referenced
this pull request
Jan 3, 2026
…ge_heatmap (meta-pytorch#1757) Summary: Enable `plot_image_heatmap` to leverage the new `draw_mask_border` and `draw_mask_legend` utilities when the input has mask segments. This provides better visualization for image attribution with discrete regions, displaying attribution colors per segment with borders and labels derived from the salience values. Differential Revision: D90038941
aobo-y
added a commit
to aobo-y/captum
that referenced
this pull request
Jan 5, 2026
…ge_heatmap (meta-pytorch#1757) Summary: Enable `plot_image_heatmap` to leverage the new `draw_mask_border` and `draw_mask_legend` utilities when the input has mask segments. This provides better visualization for image attribution with discrete regions, displaying attribution colors per segment with borders and labels derived from the salience values. Reviewed By: craymichael Differential Revision: D90038941
aobo-y
added a commit
to aobo-y/captum
that referenced
this pull request
Jan 5, 2026
…ge_heatmap (meta-pytorch#1757) Summary: Enable `plot_image_heatmap` to leverage the new `draw_mask_border` and `draw_mask_legend` utilities when the input has mask segments. This provides better visualization for image attribution with discrete regions, displaying attribution colors per segment with borders and labels derived from the salience values. Reviewed By: craymichael Differential Revision: D90038941
aobo-y
added a commit
to aobo-y/captum
that referenced
this pull request
Jan 5, 2026
…ge_heatmap (meta-pytorch#1757) Summary: Enable `plot_image_heatmap` to leverage the new `draw_mask_border` and `draw_mask_legend` utilities when the input has mask segments. This provides better visualization for image attribution with discrete regions, displaying attribution colors per segment with borders and labels derived from the salience values. Reviewed By: craymichael Differential Revision: D90038941
Contributor
|
This pull request has been merged in 8264e2d. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary: Enable
plot_image_heatmapto leverage the newdraw_mask_borderanddraw_mask_legendutilities when the input has mask segments. This provides better visualization for image attribution with discrete regions, displaying attribution colors per segment with borders and labels derived from the salience values.Differential Revision: D90038941