Name
Abstract | ||
|---|---|---|
We study a class of computer vision settings wherein one can modify the design of the objects being recognized. We develop a framework that leverages this capability---and deep networks' unusual sensitivity to input perturbations---to design ``robust objects,'' i.e., objects that are explicitly optimized to be confidently classified. Our framework yields improved performance on standard benchmarks, a simulated robotics environment, and physical-world experiments. |
Year | Venue | DocType |
|---|---|---|
2021 | Annual Conference on Neural Information Processing Systems | Conference |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
6 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Hadi Salman | 1 | 0 | 0.68 |
| Andrew Ilyas | 2 | 130 | 10.21 |
| Logan Engstrom | 3 | 117 | 7.05 |
| Sai Vemprala | 4 | 1 | 3.73 |
| Aleksander Mądry | 5 | 961 | 45.38 |
| Ashish Kapoor | 6 | 1833 | 119.72 |