Technical Program

Paper Detail

Paper: PS-1B.30
Session: Poster Session 1B
Location: H Fl├Ąche 1.OG
Session Time: Saturday, September 14, 16:30 - 19:30
Presentation Time:Saturday, September 14, 16:30 - 19:30
Presentation: Poster
Publication: 2019 Conference on Cognitive Computational Neuroscience, 13-16 September 2019, Berlin, Germany
Paper Title: Human uncertainty improves object classification
Manuscript:  Click here to view manuscript
License: Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 Unported License.
DOI: https://doi.org/10.32470/CCN.2019.1054-0
Authors: Joshua Peterson, Ruairidh Battleday, Thomas Griffiths, Princeton University, United States
Abstract: Despite the continued improvement in deep network classifiers, humans remain the enduring gold standard for strong generalization and robustness. In this work, we show that incorporating more human-like perceptual uncertainty into classification models can help narrow this gap. In particular, we show that training state-of-the-art convolutional neural networks with human-derived distributions over labels, as opposed to ground-truth labels, improves their generalization to out-of-sample datasets and robustness to adversarial attacks. These findings suggest that more accurately capturing uncertainty over image labels is critical to forming a robust visual model of the world. To facilitate further advancements of this kind, we propose our human-derived "soft" label distributions for the CIFAR10 test set, which we call CIFAR10H, as a new benchmark.