most citedIncreasing Shape Bias in ImageNet-Trained Networks Using Transfer Learning and Domain-Adversarial Methods

6 citations · 6 across the 1 of their papers we have counts for

collaborators

1 paper

cs.CV2019★ 6 cited

Increasing Shape Bias in ImageNet-Trained Networks Using Transfer Learning and Domain-Adversarial Methods

Francis Brochu

Convolutional Neural Networks (CNNs) have become the state-of-the-art method to learn from image data. However, recent research shows that they may include a texture and colour bia…