LearningCausalSemanticRepresentationfor Out-of-DistributionPrediction
–Neural Information Processing Systems
Popular models for predicting the output (or label, response, outcome)yfrom theinput (orcovariate)xhavebeenfound erroneous when confronted with a distribution change, even from an essentially irrelevant perturbation like a position shift or background change forimages [91,6,102,41,2,27].
Neural Information Processing Systems
Feb-8-2026, 03:06:56 GMT
- Country:
- North America
- Puerto Rico (0.04)
- United States
- New Jersey (0.04)
- California (0.04)
- Canada
- Quebec > Montreal (0.04)
- British Columbia > Metro Vancouver Regional District
- Vancouver (0.04)
- Alberta > Census Division No. 15
- Improvement District No. 9 > Banff (0.04)
- Europe > Italy
- Asia
- Middle East > Jordan (0.05)
- China > Beijing
- Beijing (0.04)
- Africa > Ethiopia
- Addis Ababa > Addis Ababa (0.04)
- North America
- Technology: