Search Results for author:
Found 4 papers, 2 papers with code
PEEB: Part-based Image Classifiers with an Explainable and Editable Language Bottleneck
CLIP-based classifiers rely on the prompt containing a {class name} that is known to the text encoder.
How explainable are adversarially-robust CNNs?
Here, we perform the first, large-scale evaluation of the relations of the three criteria using 9 feature-importance methods and 12 ImageNet-trained CNNs that are of 3 training algorithms and 5 CNN architectures.
The shape and simplicity biases of adversarially robust ImageNet-trained CNNs
Increasingly more similarities between human vision and convolutional neural networks (CNNs) have been revealed in the past few years.
Neurons Activation Visualization and Information Theoretic Analysis
In this work, the entropy analysis is leveraged to study the neurons activation behavior of the fully connected layers of DNNs.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
