Natural Adversarial Objects

no code implementations • 7 Nov 2021 • Felix Lau, Nishant Subramani, Sasha Harrison, Aerin Kim, Elliot Branson, Rosanne Liu

Moreover, by comparing a variety of object detection architectures, we find that better performance on MSCOCO validation set does not necessarily translate to better performance on NAO, suggesting that robustness cannot be simply achieved by training a more accurate model.

Object object-detection +1

On The State of Data In Computer Vision: Human Annotations Remain Indispensable for Developing Deep Learning Models

no code implementations • 31 Jul 2021 • Zeyad Emam, Andrew Kondrich, Sasha Harrison, Felix Lau, Yushi Wang, Aerin Kim, Elliot Branson

High-quality labeled datasets play a crucial role in fueling the development of machine learning (ML), and in particular the development of deep learning (DL).

Continual Learning