3 papers
cs.DL2019
Research Frontiers in Transfer Learning -- a systematic and bibliometric review
Frederico Guth, Teofilo Emidio de-Campos
Humans can learn from very few samples, demonstrating an outstanding generalization ability that learning algorithms are still far from reaching. Currently, the most successful mod…
cs.CV2019
Domain adaptation for holistic skin detection
Aloisio Dourado, Frederico Guth, Teofilo Emidio de Campos +1
Human skin detection in images is a widely studied topic of Computer Vision for which it is commonly accepted that analysis of pixel color or local patches may suffice. This is bec…
cs.CV2018
Skin lesion segmentation using U-Net and good training strategies
Fred Guth, Teofilo E. deCampos
In this paper we approach the problem of skin lesion segmentation using a convolutional neural network based on the U-Net architecture. We present a set of training strategies that…