Tweeted By @slashML
ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness https://t.co/ioRF2NpDvC
— /MachineLearning (@slashML) July 2, 2019
ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness https://t.co/ioRF2NpDvC
— /MachineLearning (@slashML) July 2, 2019