116 citations · 626 across the 37 of their papers we have counts for
Showing 2022Show all
2 papers · 1 filter
cs.CV2022★ 2 cited
Transfer Learning for Segmentation Problems: Choose the Right Encoder and Skip the Decoder
Jonas Dippel, Matthias Lenga, Thomas Goerttler +2
It is common practice to reuse models initially trained on different data to increase downstream task performance. Especially in the computer vision domain, ImageNet-pretrained wei…
cs.LG2022★ 1 cited
Similarity of Pre-trained and Fine-tuned Representations
Thomas Goerttler, Klaus Obermayer
In transfer learning, only the last part of the networks - the so-called head - is often fine-tuned. Representation similarity analysis shows that the most significant change still…