Last Layer Retraining of Selectively Sampled Wild Data Improves Performance
While AI models perform well in labs where training and testing data are in a similar domain, they experience significant drops in performance in the wild where the data can lie in domains outside the training distribution. Out-of-distribution (OOD) generalization is difficult because these domains...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Published: |
Massachusetts Institute of Technology
2023
|
| Online Access: | https://hdl.handle.net/1721.1/151358 |