Ask a Question

Prefer a chat interface with context about you and your work?

Human Uncertainty Makes Classification More Robust

Human Uncertainty Makes Classification More Robust

The classification performance of deep neural networks has begun to asymptote at near-perfect levels. However, their ability to generalize outside the training set and their robustness to adversarial attacks have not. In this paper, we make progress on this problem by training with full label distributions that reflect human perceptual …