Reserve the DisjointCNN name for the port, move aeon's results aside - #25
Merged
Conversation
aeon's results are renamed to DisjointCNN-Aeon and kept, rather than deleted: they are the evidence for aeon issue #3775, where a Permute after the final block leaves GlobalAveragePooling2D reducing the wrong axes so the classifier head receives one feature instead of 64, putting it about 20 accuracy points below the published numbers on all 23 shared datasets. They stay excluded from the leaderboard for the same reason as before, that listing them would read as a claim about the method rather than about one implementation. The exclusion and its explanation move with the name. DisjointCNN is now free for the port, which follows the authors' training procedure and reaches 0.952 on ERing against 0.964 published, where aeon manages 0.641. Nothing reports under that name until the run lands, so the leaderboard has no DisjointCNN row in the meantime. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
aeon's results are renamed to DisjointCNN-Aeon and kept, rather than deleted: they are the evidence for aeon issue #3775, where a Permute after the final block leaves GlobalAveragePooling2D reducing the wrong axes so the classifier head receives one feature instead of 64, putting it about 20 accuracy points below the published numbers on all 23 shared datasets.
They stay excluded from the leaderboard for the same reason as before, that listing them would read as a claim about the method rather than about one implementation. The exclusion and its explanation move with the name.
DisjointCNN is now free for the port, which follows the authors' training procedure and reaches 0.952 on ERing against 0.964 published, where aeon manages 0.641. Nothing reports under that name until the run lands, so the leaderboard has no DisjointCNN row in the meantime.
Summary
Checklist
results/schema.md.