๐
๐
Old Age
Exploring Content Relationships for Distilling Efficient GANs
December 21, 2022 ยท Entered Twilight ยท ๐ arXiv.org
Repo contents: README.md, data, datasets, distill.py, distillers, imgs, latency.py, metric, models, options, relation_kd.py, requirements.txt, scripts, test.py, trainer.py, utils
Authors
Lizhou You, Mingbao Lin, Tie Hu, Fei Chao, Rongrong Ji
arXiv ID
2212.11091
Category
cs.CV: Computer Vision
Citations
4
Venue
arXiv.org
Repository
https://github.com/TheKernelZ/CRD
โญ 3
Last Checked
3 months ago
Abstract
This paper proposes a content relationship distillation (CRD) to tackle the over-parameterized generative adversarial networks (GANs) for the serviceability in cutting-edge devices. In contrast to traditional instance-level distillation, we design a novel GAN compression oriented knowledge by slicing the contents of teacher outputs into multiple fine-grained granularities, such as row/column strips (global information) and image patches (local information), modeling the relationships among them, such as pairwise distance and triplet-wise angle, and encouraging the student to capture these relationships within its output contents. Built upon our proposed content-level distillation, we also deploy an online teacher discriminator, which keeps updating when co-trained with the teacher generator and keeps freezing when co-trained with the student generator for better adversarial training. We perform extensive experiments on three benchmark datasets, the results of which show that our CRD reaches the most complexity reduction on GANs while obtaining the best performance in comparison with existing methods. For example, we reduce MACs of CycleGAN by around 40x and parameters by over 80x, meanwhile, 46.61 FIDs are obtained compared with these of 51.92 for the current state-of-the-art. Code of this project is available at https://github.com/TheKernelZ/CRD.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
๐ Similar Papers
In the same crypt โ Computer Vision
๐
๐
Old Age
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
๐
๐
Old Age
SSD: Single Shot MultiBox Detector
๐
๐
Old Age
Squeeze-and-Excitation Networks
๐
๐
Old Age
Fast R-CNN
๐
๐
Old Age