38 papers with code • 2 benchmarks • 3 datasets
Its principled nature also enables us to identify methods for both training and attacking neural networks that are reliable and, in a certain sense, universal.
Ranked #2 on Robust classification on CIFAR-10
To highlight, RP with a CNN classifier can predict if an MNIST digit is a "one"or "not" with only 0. 25% error, and 0. 46 error across all digits, even when 50% of positive examples are mislabeled and 50% of observed positive labels are mislabeled negative examples.
Following these guidelines, we design our Fully Convolutional Siamese tracker++ (SiamFC++) by introducing both classification and target state estimation branch(G1), classification score without ambiguity(G2), tracking without prior knowledge(G3), and estimation quality score(G4).
Energy based models (EBMs) are appealing due to their generality and simplicity in likelihood modeling, but have been traditionally difficult to train.
Ranked #3 on Image Generation on Stacked MNIST
We show how to turn any classifier that classifies well under Gaussian noise into a new classifier that is certifiably robust to adversarial perturbations under the $\ell_2$ norm.
Ranked #2 on Robust classification on ImageNet
This work contributes the first large, public, multiclass image dataset of weed species from the Australian rangelands; allowing for the development of robust classification methods to make robotic weed control viable.