Supplementary material for testing deep image classifiers using generative machine learning (DPhil thesis)
This data is supplementary to Isaac Dunn's DPhil thesis, the abstract of which follows. Although deep neural networks (DNNs) attain excellent performance on the specific tasks they are trained for, this often seems to be obtained using easier-to-learn proxies for the truly relevant concepts. T...
| Autore principale: | |
|---|---|
| Natura: | Dataset |
| Lingua: | English |
| Pubblicazione: |
University of Oxford
2022
|
| Soggetti: |