The developmental trajectory of object recognition robustness: children are like small adults but unlike big deep neural networks. (arXiv:2205.10144v1 [cs.CV])

In laboratory object recognition tasks based on undistorted photographs, both
adult humans and Deep Neural Networks (DNNs) perform close to ceiling. Unlike
adults', whose object recognition performance is robust against a wide range of
image distortions, DNNs trained on standard ImageNet (1.3M images) perform
poorly on distorted images. However, the last two years have seen impressive
gains in DNN distortion robustness, predominantly achieved through
ever-increasing large-scale datasets$\unicode{x2014}$orders of magnitude larger
than ImageNet. While this simple brute-force approach is very effective …

arxiv big children cv networks neural networks robustness small