{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/mix-and-match-networks-encoder-decoder","title":"Mix and match networks: encoder-decoder alignment for zero-pair image translation","arxiv_id":"1804.02199","date":"2018-04-06","proceeding":"CVPR 2018 6","authors":["Yaxing Wang","Joost Van de Weijer","Luis Herranz"],"abstract":"We address the problem of image translation between domains or modalities for\nwhich no direct paired data is available (i.e. zero-pair translation). We\npropose mix and match networks, based on multiple encoders and decoders aligned\nin such a way that other encoder-decoder pairs can be composed at test time to\nperform unseen image translation tasks between domains or modalities for which\nexplicit paired samples were not seen during training. We study the impact of\nautoencoders, side information and losses in improving the alignment and\ntransferability of trained pairwise translation models to unseen translations.\nWe show our approach is scalable and can perform colorization and style\ntransfer between unseen combinations of domains. We evaluate our system in a\nchallenging cross-modal setting where semantic segmentation is estimated from\ndepth images, without explicit access to any depth-semantic segmentation\ntraining pairs. Our model outperforms baselines based on pix2pix and CycleGAN\nmodels.","url_abs":"http://arxiv.org/abs/1804.02199v1","url_pdf":"http://arxiv.org/pdf/1804.02199v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"mix-and-match-networks-encoder-decoder","repo_url":"https://github.com/yaxingwang/Mix-and-match-networks","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"colorization","task_name":"Colorization"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"style-transfer","task_name":"Style Transfer"},{"task_slug":"translation","task_name":"Translation"}],"methods":[{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"colorization","method_name":"Colorization"},{"method_slug":"concatenated-skip-connection","method_name":"Concatenated Skip Connection"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"cycle-consistency-loss","method_name":"Cycle Consistency Loss"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gan-least-squares-loss","method_name":"GAN Least Squares Loss"},{"method_slug":"instance-normalization","method_name":"Instance Normalization"},{"method_slug":"patchgan","method_name":"PatchGAN"},{"method_slug":"pix2pix","method_name":"Pix2Pix"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1804.02199","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}