Kumar Reddy, NK and Killedar, V and Seelamantula, CS (2023) Quantized Generative Models for Solving Inverse Problems. In: UNSPECIFIED, pp. 1520-1525.
|
PDF
CVE_Int_Con_Com_Vis_Wor_2023.pdf - Published Version Download (1MB) | Preview |
Abstract
Generative priors have been shown to be highly successful in solving inverse problems. In this paper, we consider quantized generative models i.e., the generator network weights come from a learnt finite alphabet. Quantized neural networks are efficient in terms of memory and computation. They are ideally suited for deployment in a practical setting involving low-precision hardware. In this paper, we solve non-linear inverse problems using quantized generative models. We introduce a new meta-learning framework that makes use of proximal operators and jointly optimizes the quantized weights of the generative model, parameters of the sensing network, and the latent-space representation. Experimental validation is carried out using standard datasets - MNIST, CIFAR10, SVHN, and STL10. The results show that the performance of 32-bit networks can be achieved using 4-bit networks. The performance of 1-bit networks is about 0.7 to 2 dB inferior, while saving significantly (32�) on the model size. © 2023 IEEE.
Item Type: | Conference Paper |
---|---|
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 publisher |
Department/Centre: | Others |
Date Deposited: | 01 Mar 2024 10:08 |
Last Modified: | 01 Mar 2024 10:08 |
URI: | https://eprints.iisc.ac.in/id/eprint/84039 |
Actions (login required)
![]() |
View Item |