paper-with-me

홈 › Papers

Microdosing: Knowledge Distillation for GAN based Compression

2022-01-07 · Leonhard Helminger, Roberto Azevedo, Abdelaziz Djelouah, Markus Gross, Christopher Schroers

Recently, significant progress has been made in learned image and video compression. In particular the usage of Generative Adversarial Networks has lead to impressive results in the low bit rate regime. However, the model size remains an important issue in current state-of-the-art proposals and existing solutions require significant computation effort on the decoding side. This limits their usage in realistic scenarios and the extension to video compression. In this paper, we demonstrate how to leverage knowledge distillation to obtain equally capable image decoders at a fraction of the original number of parameters. We investigate several aspects of our solution including sequence specialization with side information for image coding. Finally, we also show how to transfer the obtained benefits into the setting of video compression. Overall, this allows us to reduce the model size by a factor of 20 and to achieve 50% reduction in decoding time.

📄 PDF Abstract BibTeX arXiv:2201.02624

Code (0)

등록된 구현이 없습니다.

Tasks

Knowledge DistillationVideo Compression

Methods 이 논문이 사용한 방법론

Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…

Similar Papers 제목 키워드 기반

A Functional Perspective on Knowledge Distillation in Neural Networks

2025-10-14 · Israel Mason-Williams, Gabryel Mason-Williams, Helen Yannakoudakis arxiv

Knowledge distillation is considered a compression mechanism when judged on the resulting student's accuracy and loss, yet its functional impact is poorly understood. We quantify the compression capacity of knowledge dis…

Knowledge Distillation

A Unified Knowledge Distillation Framework for Deep Directed Graphical Models

2021-09-29 · CVPR 2023 1 · Yizhuo Chen, Kaizhao Liang, Zhe Zeng, Yifei Yang 외

Knowledge distillation (KD) is a technique that transfers the knowledge from a large teacher network to a small student network. It has been widely applied to many different tasks, such as model compression and federate…

Continual LearningFederated LearningKnowledge DistillationModel Compression

Weight Distillation: Transferring the Knowledge in Neural Network Parameters

2020-09-19 · ACL 2021 5 · Ye Lin, Yanyang Li, Ziyang Wang, Bei Li 외

Knowledge distillation has been proven to be effective in model acceleration and compression. It allows a small network to learn to generalize in the same way as a large network. Recent successes in pre-training suggest …

Knowledge DistillationMachine TranslationTranslation

Spirit Distillation: A Model Compression Method with Multi-domain Knowledge Transfer

2021-04-29 · Zhiyuan Wu, Yu Jiang, Minghao Zhao, Chupeng Cui 외

Recent applications pose requirements of both cross-domain knowledge transfer and model compression to machine learning models due to insufficient training data and limited computational resources. In this paper, we prop…

General KnowledgeKnowledge DistillationModel CompressionTransfer Learning

Model compression using knowledge distillation with integrated gradients

2025-06-17 · David E. Hernandez, Jose Chang, Torbjörn E. M. Nordling

Model compression is critical for deploying deep learning models on resource-constrained devices. We introduce a novel method enhancing knowledge distillation with integrated gradients (IG) as a data augmentation strateg…

Data AugmentationKnowledge DistillationModel Compression