REVIEW 1 cited by
Missingness Bias in Model Debugging
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Missingness, or the absence of features from an input, is a concept fundamental to many model debugging tools. However, in computer vision, pixels cannot simply be removed from an image. One thus tends to resort to heuristics such as blacking out pixels, which may in turn introduce bias into the debugging process. We study such biases and, in particular, show how transformer-based architectures can enable a more natural implementation of missingness, which side-steps these issues and improves the reliability of model debugging in practice. Our code is available at https://github.com/madrylab/missingness
Forward citations
Cited by 1 Pith paper
-
Detecting Regional Spurious Correlations in Vision Transformers via Token Discarding
A token-discarding method for vision transformers measures whether predictions rely on features outside the object's bounding box, identifying spurious correlations and problematic ImageNet classes.
Discussion (0). Continue with ORCID to comment.