ePrints@IIScePrints@IISc Home | About | Browse | Latest Additions | Advanced Search | Contact | Help

CoroNetGAN: Controlled Pruning of GANs via Hypernetworks

Kumar, A and Anand, K and Mandloi, S and Mishra, A and Thakur, A and Kasera, N and Prathosh, AP (2023) CoroNetGAN: Controlled Pruning of GANs via Hypernetworks. In: 2023 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2023, 2 October 2023-6 October 2023, Paris, pp. 1254-1263.

[img] PDF
Pro_2023_IEEE_CVF_int_con_com_vis_wor_ICCVW_2023.pdf - Published Version
Restricted to Registered users only

Download (1MB) | Request a copy
Official URL: https://doi.org/10.1109/ICCVW60793.2023.00136


Generative Adversarial Networks (GANs) have proven to exhibit remarkable performance and are widely used across many generative computer vision applications. However, the unprecedented demand for the deployment of GANs on resource-constrained edge devices still poses a challenge due to huge number of parameters involved in the generation process. This has led to focused attention on the area of compressing GANs. Most of the existing works use knowledge distillation with the overhead of teacher dependency. Moreover, there is no ability to control the degree of compression in these methods. Hence, we propose CoroNet-GAN for compressing GAN using the combined strength of differentiable pruning method via hypernetworks. The proposed method provides the advantage of performing controllable compression while training along with reducing training time by a substantial factor. Experiments have been done on various conditional GAN architectures (Pix2Pix and CycleGAN) to signify the effectiveness of our approach on multiple benchmark datasets such as Edges � Shoes, Horse � Zebra and Summer � Winter. The results obtained illustrate that our approach succeeds to outperform the baselines on Zebra � Horse and Summer � Winter achieving the best FID score of 32.3 and 72.3 respectively, yielding high-fidelity images across all the datasets. Additionally, our approach also outperforms the state-of-the-art methods in achieving better inference time on various smart-phone chipsets and data-types making it a feasible solution for deployment on edge devices. © 2023 IEEE.

Item Type: Conference Proceedings
Publication: Proceedings - 2023 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2023
Publisher: Institute of Electrical and Electronics Engineers Inc.
Additional Information: The copyright for this article belongs to Institute of Electrical and Electronics Engineers Inc.
Department/Centre: Others
Date Deposited: 01 Mar 2024 10:09
Last Modified: 01 Mar 2024 10:09
URI: https://eprints.iisc.ac.in/id/eprint/84041

Actions (login required)

View Item View Item