Contrastive Learning for Unpaired Image-to-Image Translation

Contrastive learning has provided a huge boost in self-supervised representation learning. This paper shows that this can even improve other self-supervised learning algorithms, like generative models in the GAN framework. I am really excited about how image to image translation networks can be used for domain similarity analysis. Thanks for watching! Please Subscribe!

Paper Links:
Contrastive Unpaired Translation (contains code, video, website, and paper link): https://github.com/taesungp/contrastive-unpaired-translation
Contrastive Predictive Coding: https://arxiv.org/pdf/1905.09272.pdf
SinGAN: https://arxiv.org/pdf/1905.01164.pdf
EfficientDet: https://arxiv.org/pdf/1911.09070.pdf
Feature Pyramid Networks for Object Detection: https://arxiv.org/pdf/1612.03144.pdf
Don't Stop Pretraining: https://arxiv.org/pdf/2004.10964.pdf
CycleGAN: https://arxiv.org/pdf/1703.10593.pdf
SimCLR: https://arxiv.org/pdf/2002.05709.pdf
MoCo: https://arxiv.org/pdf/1911.05722.pdf
On the Measure of Intelligence: https://arxiv.org/pdf/1911.01547.pdf

Chapters
0:00 Beginning
1:37 Image-to-Image Translation
2:42 Example with Robots! (AVID)
3:26 High-level overview of algorithm
4:23 How Image Patches are Compared
6:53 PatchNCE Loss
7:52 MLP Projection Head
8:48 PatchNCE Loss (Equation)
10:52 External Negative test from Dataset rather than the Same Image
11:54 Final Objective
13:48 Ablation Takeaways
14:37 Results
15:38 Application to Domain Similarity
17:50 Interest in Domain Similarity Metrics

Видео Contrastive Learning for Unpaired Image-to-Image Translation канала Henry AI Labs