Recently, image-to-image translation methods based on contrastive learning
achieved state-of-the-art results in many tasks. However, the negatives are
sampled from the input feature spaces in the previous work, which makes the
negatives lack diversity. Moreover, in the latent space of the embedings,the
previous methods ignore domain consistency between the generated image and the
real images of target domain. In this paper, we propose a novel contrastive
learning framework for unpaired image-to-image translation, called MCCUT. We
utilize the multi-crop views to generate the negatives via the center-crop and
the random-crop, which can improve the diversity of negatives and meanwhile
increase the quality of negatives. To constrain the embedings in the deep
feature space,, we formulate a new domain consistency loss function, which
encourages the generated images to be close to the real images in the embedding
space of same domain. Furthermore, we present a dual coordinate channel
attention network by embedding positional information into SENet, which called
DCSE module. We employ the DCSE module in the design of generator, which makes
the generator pays more attention to channels with greater weight. In many
image-to-image translation tasks, our method achieves state-of-the-art results,
and the advantages of our method have been proved through extensive comparison
experiments and ablation research.

本文提出了一种新颖的基于对比学习的无配对图像翻译框架 MCCUT，通过多视图裁剪生成多样化的负样本，利用领域一致性误差函数将深度特征空间中的嵌入约束在一起，并采用 DCSE 模块来设计生成器以获得更好的结果。

无监督图像翻译的多作物对比学习

Multi-crop Contrastive Learning for Unsupervised Image-to-Image  Translation

We propose new filtering algorithms for the SEQUENCE constraint and some
extensions of the SEQUENCE constraint based on network flows. We enforce domain
consistency on the SEQUENCE constraint in $O(n^2)$ time down a branch of the
search tree. This improves upon the best existing domain consistency algorithm
by a factor of $O(\log n)$. The flows used in these algorithms are derived from
a linear program. Some of them differ from the flows used to propagate global
constraints like GCC since the domains of the variables are encoded as costs on
the edges rather than capacities. Such flows are efficient for maintaining
bounds consistency over large domains and may be useful for other global
constraints.

研究提出了基于网络流的 SEQUENCE 约束条件的滤波算法及其扩展，通过使用基于线性规划的流算法，能够更加高效地维护对大型域的约束一致性。