Search Results for author:
Found 6 papers, 2 papers with code
How Robust Are Energy-Based Models Trained With Equilibrium Propagation?
Deep neural networks (DNNs) are easily fooled by adversarial perturbations that are imperceptible to humans.
DeepPatent2: A Large-Scale Benchmarking Corpus for Technical Drawing Understanding
CV tasks, such as image captioning, which has primarily been carried out on natural images, still struggle to produce accurate and meaningful captions on sketched images often included in scientific and technical documents.
Robustness to Label Noise Depends on the Shape of the Noise Distribution in Feature Space
However, for the special case of class-dependent label noise (independent of features given the class label), the tipping point can be as low as 50%.
DeepPatent: Large scale patent drawing recognition and retrieval
First, we introduce DeepPatent, a new large-scale dataset for recognition and retrieval of design patent drawings.
Ranked #3 on
Image Retrieval
on DeepPatent
On visual self-supervision and its effect on model robustness
We identify primary ways in which self-supervision can be added to adversarial training, and observe that using a self-supervised loss to optimize both network parameters and find adversarial examples leads to the strongest improvement in model robustness, as this can be viewed as a form of ensemble adversarial training.
Transfer learning with fewer ImageNet classes
Though much previous work tried to uncover the best practices for transfer learning, much is left unexplored.
