Abstract
The unsupervised image-to-image translation aims to learn a mapping that translates images from one domain to the target domain. Current state-of-the-art generative adversarial network (GAN) models utilize time and space-costly operators to produce impressive translated images. However, further research and model deployment are under restrictions due to the high computational costs of the models. In order to resolve the problem, we enhance the GAN structure by employing a lightweight operator named involution that facilitates extracting both local features and long-range dependencies across channels. Besides, we also notice that previous works attach less importance to feature-level reconstruction discrepancy between original and reconstructed images. Nevertheless, such information is crucial in improving the quality of the synthesized images. Thus, we develop a novel loss term that evaluates the learned perceptual similarity distance to regulate the training process. The qualitative and quantitative experiment results on several prevailing benchmarks demonstrate that our model, dubbed InvolutionGAN, could produce competitive image results while saving computational costs up to 91.9%. In addition, extensive ablation studies are conducted to search for the best model structure and verify that each component we introduced is effective.
Similar content being viewed by others
Data Availability Statements
All data and results included in this study are available upon reasonable request by contact with the corresponding author.
References
Aguinaldo A, Chiang PY, Gain A, et al (2019) Compressing gans using knowledge distillation. arXiv preprint arXiv:1902.00159
Arjovsky M, Chintala S, Bottou L (2017) Wasserstein generative adversarial networks. In: International conference on machine learning, PMLR, pp 214–223
Bharti V, Biswas B, Shukla KK (2021) Emocgan: a novel evolutionary multiobjective cyclic generative adversarial network and its application to unpaired image translation. Neural Comput Appl, pp 1–15
Bińkowski M, Sutherland DJ, Arbel M, et al (2018) Demystifying mmd gans. arXiv preprint arXiv:1801.01401
Cao Y, Zhou Z, Zhang W, et al (2017) Unsupervised diverse colorization via generative adversarial networks. In: Joint European conference on machine learning and knowledge discovery in databases, Springer, pp 151–166
Chen R, Huang W, Huang B, et al (2020) Reusing discriminators for encoding: Towards unsupervised image-to-image translation. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 8168–8177
Chen X, Duan Y, Houthooft R, et al (2016) Infogan: interpretable representation learning by information maximizing generative adversarial nets. In: Proceedings of the 30th international conference on neural information processing systems, pp 2180–2188
Choi Y, Choi M, Kim M, et al (2018) Stargan: Unified generative adversarial networks for multi-domain image-to-image translation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 8789–8797
Choi Y, Uh Y, Yoo J, et al (2020) Stargan v2: diverse image synthesis for multiple domains. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 8188–8197
Emami H, Aliabadi MM, Dong M et al (2020) Spa-gan: spatial attention gan for image-to-image translation. IEEE Trans Multimed 23:391–401
Goodfellow I, Pouget-Abadie J, Mirza M, et al (2014) Generative adversarial nets. Adv Neural Inf Process Syst 27
Gulrajani I, Ahmed F, Arjovsky M, et al (2017) Improved training of wasserstein gans. arXiv preprint arXiv:1704.00028
He K, Zhang X, Ren S, et al (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770–778
Heusel M, Ramsauer H, Unterthiner T, et al (2017) Gans trained by a two time-scale update rule converge to a local nash equilibrium. Adv Neural Inf Process Syst 30
Huang X, Liu MY, Belongie S, et al (2018) Multimodal unsupervised image-to-image translation. In: Proceedings of the European conference on computer vision (ECCV), pp 172–189
Iizuka S, Simo-Serra E, Ishikawa H (2016) Let there be color! joint end-to-end learning of global and local image priors for automatic image colorization with simultaneous classification. ACM Trans Graph 35(4):1–11
Isola P, Zhu JY, Zhou T, et al (2017) Image-to-image translation with conditional adversarial networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1125–1134
Jeong S, Kim Y, Lee E, et al (2021) Memory-guided unsupervised image-to-image translation. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 6558–6567
Jo Y, Yang S, Kim SJ (2020) Investigating loss functions for extreme super-resolution. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition workshops, pp 424–425
Johnson J, Alahi A, Fei-Fei L (2016) Perceptual losses for real-time style transfer and super-resolution. In: European conference on computer vision, Springer, pp 694–711
Kang T, Lee KH (2020) Unsupervised image-to-image translation with self-attention networks. In: 2020 IEEE international conference on big data and smart computing (BigComp), IEEE, pp 102–108
Kim J, Kim M, Kang H, et al (2019) U-gat-it: unsupervised generative attentional networks with adaptive layer-instance normalization for image-to-image translation. arXiv preprint arXiv:1907.10830
Kim T, Cha M, Kim H, et al (2017) Learning to discover cross-domain relations with generative adversarial networks. In: International conference on machine learning, PMLR, pp 1857–1865
Kingma DP, Ba J (2014) Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980
Ledig C, Theis L, Huszár F, et al (2017) Photo-realistic single image super-resolution using a generative adversarial network. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4681–4690
Lee HY, Tseng HY, Huang JB, et al (2018) Diverse image-to-image translation via disentangled representations. In: Proceedings of the European conference on computer vision (ECCV), pp 35–51
Lee HY, Tseng HY, Mao Q et al (2020) Drit++: diverse image-to-image translation via disentangled representations. Int J Comput Vis 128(10):2402–2417
Li D, Hu J, Wang C, et al (2021) Involution: inverting the inherence of convolution for visual recognition. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 12321–12330
Li M, Lin J, Ding Y, et al (2020) Gan compression: Efficient architectures for interactive conditional gans. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 5284–5294
Liu MY, Breuel T, Kautz J (2017) Unsupervised image-to-image translation networks. In: Advances in neural information processing systems, pp 700–708
Mao Q, Tseng HY, Lee HY et al (2022) Continuous and diverse image-to-image translation via signed attribute vectors. Int J Comput Vis 130(2):517–549
Mao X, Li Q, Xie H, et al (2017) Least squares generative adversarial networks. In: Proceedings of the IEEE international conference on computer vision, pp 2794–2802
Mejjati YA, Richardt C, Tompkin J, et al (2018) Unsupervised attention-guided image to image translation. arXiv preprint arXiv:1806.02311
Mirza M, Osindero S (2014) Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784
Peng X, Peng S, Hu Q, et al (2022) Contour-enhanced cyclegan framework for style transfer from scenery photos to Chinese landscape paintings. Neural Comput Appl, pp 1–22
Qi GJ (2020) Loss-sensitive generative adversarial networks on lipschitz densities. Int J Comput Vis 128(5):1118–1140
Qu X, Wang X, Wang Z, et al (2018) Perceptual-dualgan: perceptual losses for image to image translation with generative adversarial nets. In: 2018 international joint conference on neural networks (IJCNN), IEEE, pp 1–8
Radford A, Metz L, Chintala S (2015) Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv preprint arXiv:1511.06434
Shi W, Caballero J, Huszár F, et al (2016) Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1874–1883
Tang H, Xu D, Sebe N, et al (2019) Multi-channel attention selection gan with cascaded semantic guidance for cross-view image translation. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 2417–2426
Ulyanov D, Vedaldi A, Lempitsky V (2016) Instance normalization: the missing ingredient for fast stylization. arXiv preprint arXiv:1607.08022
Wang TC, Liu MY, Zhu JY, et al (2018) High-resolution image synthesis and semantic manipulation with conditional gans. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 8798–8807
Xiao J, Zhang S, Yao Y et al (2022) Generative adversarial network with hybrid attention and compromised normalization for multi-scene image conversion. Neural Comput Appl 34(9):7209–7225
Xu S, Zhu Q, Wang J (2020) Generative image completion with image-to-image translation. Neural Comput Appl 32(11):7333–7345
Yadav NK, Singh SK, Dubey SR (2022) Csa-gan: cyclic synthesized attention guided generative adversarial network for face synthesis. Appl Intell, pp 1–20
Yi Z, Zhang H, Tan P, et al (2017) Dualgan: Unsupervised dual learning for image-to-image translation. In: Proceedings of the IEEE international conference on computer vision, pp 2849–2857
Zhang R, Isola P, Efros AA (2016) Colorful image colorization. In: European conference on computer vision, Springer, pp 649–666
Zhang Y, Yu L, Sun B, et al (2022) Eng-face: cross-domain heterogeneous face synthesis with enhanced asymmetric cyclegan. Appl Intell pp 1–13
Zhou D, Zhang H, Li Q, et al (2022) Coutfitgan: learning to synthesize compatible outfits supervised by silhouette masks and fashion styles. IEEE Trans Multimed
Zhu JY, Park T, Isola P, et al (2017) Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of the IEEE international conference on computer vision, pp 2223–2232
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
Haipeng Deng, Qiuxia Wu, Han Huang, Xiaowei Yang and Zhiyong Wang declare that no conflict of interest could have appeared to influence the work reported in this paper.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Deng, H., Wu, Q., Huang, H. et al. InvolutionGAN: lightweight GAN with involution for unsupervised image-to-image translation. Neural Comput & Applic 35, 16593–16605 (2023). https://doi.org/10.1007/s00521-023-08530-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-023-08530-z