MC-I2I: Multi-Cycle Guided Unpaired Image-to-Image Translation on Industrial Long-Tail Data
ACM Transactions on Autonomous and Adaptive Systems · 29.07.2026
DOI: 10.1145/3831590 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Autonomous and Adaptive Systems, online erschienen am 29.07.2026. Verfasst von Zheng Wu und 4 weiteren Autor:innen. Die Arbeit nennt 45 Literaturangaben.
Abstract (Originalsprache)
Autonomous vision systems in modern industry must routinely translate images across unpaired and highly imbalanced domains, where rare target-domain patterns are severely underrepresented. Existing unpaired translation methods tend to degrade under such severe imbalance. To address this challenge, we propose MC-I2I, a multi-cycle guided image translation framework that integrates three complementary mechanisms. Dual-Cycle Latent Consistency imposes self-cycle and cross-cycle constraints in latent space to suppress representation drift caused by data imbalance. Dual-Branch Guided Reconstruction balances discriminability and diversity by alternately freezing the encoder and decoder, enabling each branch to receive dense pixel-level gradients from its fixed counterpart. Generator-Led Pseudo Cycle allows the generator to guide the discriminator toward learning rare target-domain characteristics, thereby improving sensitivity to scarce operating conditions. Extensive experiments across multiple tasks show that MC-I2I consistently improves translation fidelity and remains robust under severe long-tail conditions.
Zitieren
APA
Wu, Z., Guo, K., Zhang, Z., Ding, R., & Zhou, X. (2026). MC-I2I: Multi-Cycle Guided Unpaired Image-to-Image Translation on Industrial Long-Tail Data. ACM Transactions on Autonomous and Adaptive Systems. https://doi.org/10.1145/3831590
Vancouver
Wu Z, Guo K, Zhang Z, Ding R, Zhou X. MC-I2I: Multi-Cycle Guided Unpaired Image-to-Image Translation on Industrial Long-Tail Data. ACM Transactions on Autonomous and Adaptive Systems. 2026. doi:10.1145/3831590
BibTeX
@article{Wu2026,
author = {Wu, Zheng and Guo, Kehua and Zhang, Zhuo and Ding, Rui and Zhou, Xiaokang},
title = {MC-I2I: Multi-Cycle Guided Unpaired Image-to-Image Translation on Industrial Long-Tail Data},
journal = {ACM Transactions on Autonomous and Adaptive Systems},
year = {2026},
doi = {10.1145/3831590}
}
EUVIMED