paper-with-me

Papers

SDAKD: Student Discriminator Assisted Knowledge Distillation for Super-Resolution Generative Adversarial Networks

2025-10-04 · Nikolaos Kaparinos, Vasileios Mezaris arxiv

Generative Adversarial Networks (GANs) achieve excellent performance in generative tasks, such as image super-resolution, but their computational requirements make difficult their deployment on resource-constrained devices. While knowledge distillation is a promising research direction for GAN compression, effectively training a smaller student generator is challenging due to the capacity mismatch between the student generator and the teacher discriminator. In this work, we propose Student Discriminator Assisted Knowledge Distillation (SDAKD), a novel GAN distillation methodology that introduces a student discriminator to mitigate this capacity mismatch. SDAKD follows a three-stage training strategy, and integrates an adapted feature map distillation approach in its last two training stages. We evaluated SDAKD on two well-performing super-resolution GANs, GCFSR and Real-ESRGAN. Our experiments demonstrate consistent improvements over the baselines and SOTA GAN knowledge distillation methods. The SDAKD source code will be made openly available upon acceptance of the paper.

📄 PDF Abstract BibTeX arXiv:2510.03870

Code (0)

등록된 구현이 없습니다.

Tasks

Knowledge DistillationImage Super-Resolution

Similar Papers 제목 키워드 기반

Compressing Deep Graph Neural Networks via Adversarial Knowledge Distillation

2022-05-24 · Huarui He, Jie Wang, Zhanqiu Zhang, Feng Wu

Deep graph neural networks (GNNs) have been shown to be expressive for modeling graph-structured data. Nevertheless, the over-stacked architecture of deep graph models makes it difficult to deploy and rapidly test on mob…

Graph ClassificationKnowledge DistillationNode Classification

AI-KD: Adversarial learning and Implicit regularization for self-Knowledge Distillation

2022-11-20 · Hyungmin Kim, Sungho Suh, SungHyun Baek, Daehwan Kim 외

We present a novel adversarial penalized self-knowledge distillation method, named adversarial learning and implicit regularization for self-knowledge distillation (AI-KD), which regularizes the training procedure by adv…

Knowledge DistillationSelf-Knowledge Distillation

Black-Box On-Policy Distillation of Large Language Models

2025-11-13 · Tianzhu Ye, Li Dong, Zewen Chi, Xun Wu 외 arxiv

Black-box distillation creates student large language models (LLMs) by learning from a proprietary teacher model's text outputs alone, without access to its internal logits or parameters. In this work, we introduce Gener…

Knowledge Distillation

Dual Discriminator Adversarial Distillation for Data-free Model Compression

2021-04-12 · Haoran Zhao, Xin Sun, Junyu Dong, Hui Yu 외

Knowledge distillation has been widely used to produce portable and efficient neural networks which can be well applied on edge devices for computer vision tasks. However, almost all top-performing knowledge distillation…

Data-free Knowledge DistillationKnowledge DistillationModel CompressionSemantic Segmentation

Feature Adversarial Distillation for Point Cloud Classification

2023-06-25 · YuXing Lee, Wei Wu

Due to the point cloud's irregular and unordered geometry structure, conventional knowledge distillation technology lost a lot of information when directly used on point cloud tasks. In this paper, we propose Feature Adv…

ClassificationFADKnowledge DistillationModel Compression+2