no code implementations • 28 Sep 2023 • Ben Lonnqvist, Zhengqing Wu, Michael H. Herzog
Humans are able to segment images effortlessly without supervision using perceptual grouping.
no code implementations • 2 Aug 2022 • Ben Lonnqvist, Harshitha Machiraju, Michael H. Herzog
In a recent article, Guo et al. [arXiv:2206. 11228] report that adversarially trained neural representations in deep networks may already be as robust as corresponding primate IT neural representations.
no code implementations • 1 Mar 2019 • Ben Lonnqvist, Alasdair D. F. Clarke, Ramakrishna Chakravarthi
We found that crowding followed a predictable pattern across architectures that was different from that in humans.