Deep learning on information-rich scientific images collapses to one-dimensional predictions due to a mismatch between data priors and the model's simplicity bias, even after robustification techniques.
Rethinking the image feature biases exhib- ited by deep convolutional neural network models in image recognition
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Anatomy of a failure: When, how, and why deep vision fails in scientific domains
Deep learning on information-rich scientific images collapses to one-dimensional predictions due to a mismatch between data priors and the model's simplicity bias, even after robustification techniques.