contrastive-unpaired-translation is queued for analysis. Crawling candidates and ranking them takes a few minutes. This page updates itself when the list exists — you can also come back later.
What is known so far comes from the other direction:
These projects were analysed and named contrastive-unpaired-translation among their alternatives. The relationship is not symmetric — how contrastive-unpaired-translation rates them is a separate judgement, made when contrastive-unpaired-translation is analysed in its own right.
calls contrastive-unpaired-translation “Choose when you need faster and memory-efficient unpaired translation via contrastive learning (CUT) rather than cycle consistency.”
Image-to-Image Translation in PyTorch
calls contrastive-unpaired-translation “Choose when training speed and memory matter and you still need unpaired translation; the official CUT code is faster and lighter than CycleGAN.”
Software that can generate photos from paintings, turn horses into zebras, perform style transfer, and more.
calls contrastive-unpaired-translation “Unsupervised unpaired image translation without cycle consistency; choose for fast and lightweight training on unpaired datasets.”
Synthesizing and manipulating 2048x1024 images with conditional GANs
calls contrastive-unpaired-translation “Choose for faster unpaired translation (CUT) with a smaller memory/training footprint than CycleGAN, in a dedicated PyTorch codebase.”
PaddlePaddle GAN library, including lots of interesting applications like First-Order motion transfer, Wav2Lip, picture repair, image editing, photo2cartoon, image style transfer, GPEN, and so on.