Search Results for author:
Found 3 papers, 0 papers with code
NASTransfer: Analyzing Architecture Transferability in Large Scale Neural Architecture Search
The typical way of conducting large scale NAS is to search for an architectural building block on a small dataset (either using a proxy set from the large dataset or a completely different small scale dataset) and then transfer the block to a larger dataset.
Assessing Shape Bias Property of Convolutional Neural Networks
In order to conduct large scale experiments, we propose using the model accuracy on images with reversed brightness as a metric to evaluate the shape bias property.
On the Limitation of Convolutional Neural Networks in Recognizing Negative Images
To this end, we evaluate CNNs on negative images, since they share the same structure and semantics as regular images and humans can classify them correctly.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
