paper-with-me

홈 › Papers

Not All Regions are Worthy to be Distilled: Region-aware Knowledge Distillation Towards Efficient Image-to-Image Translation

2021-09-29 · Linfeng Zhang, Kaisheng Ma

Recent progress in image-to-image translation has witnessed the success of generative adversarial networks (GANs). However, GANs usually contain a huge number of parameters, which lead to intolerant memory and computation consumption and limit their deployment on edge devices. To address this issue, knowledge distillation is proposed to transfer the knowledge learned by a cumbersome teacher model to an efficient student model. However, previous knowledge distillation methods directly train the student to learn teacher knowledge in all the spatial regions of the images but ignore the fact that in image-to-image translation a large number of regions (e.g. background regions) should not be translated and teacher features in these regions are not worthy to be distilled. To tackle this challenge, in this paper, we propose Region-aware Knowledge Distillation which first localizes the crucial regions in the images with attention mechanism. Then, teacher features in these crucial regions are distilled to students with a region-wise contrastive learning framework. Besides distilling teacher knowledge in features, we further introduce perceptual distillation to distill teacher knowledge in the generated images. Experiments with four comparison methods demonstrate the substantial effectiveness of our method on both paired and unpaired image-to-image translation. For instance, our 7.08X compressed and 6.80X accelerated CycleGAN student outperforms its teacher by 1.36 and 1.16 FID scores on Horse to Zebra and Zebra to Horse, respectively. Codes have been released in the supplementary material and will be released on GitHub soon.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

AllContrastive LearningImage-to-Image TranslationKnowledge DistillationTranslation

Methods 이 논문이 사용한 방법론

HuMan(Expedia)||How do I get a human at Expedia? How do I get a human at Expedia? How Do I Get a Human at Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Real-Time Help & Exclusive…
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Contrastive Learning 설명 없음
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.…
PatchGAN 설명 없음
Batch Normalization 설명 없음
Residual Connection 설명 없음
Sigmoid Activation 설명 없음

Similar Papers 제목 키워드 기반

ReCo-KD: Region- and Context-Aware Knowledge Distillation for Efficient 3D Medical Image Segmentation

2026-01-13 · Qizhen Lan, Yu-Chun Hsu, Nida Saddaf Khan, Xiaoqian Jiang arxiv

Accurate 3D medical image segmentation is vital for diagnosis and treatment planning, but state-of-the-art models are often too large for clinics with limited computing resources. Lightweight architectures typically suff…

Medical Image SegmentationKnowledge Distillation

A Simple yet Effective DDG Predictor is An Unsupervised Antibody Optimizer and Explainer

2025-02-10 · Lirong Wu, Yunfan Liu, Haitao Lin, Yufei Huang 외

The proteins that exist today have been optimized over billions of years of natural evolution, during which nature creates random mutations and selects them. The discovery of functionally promising mutations is challenge…

Learning Distilled Collaboration Graph for Multi-Agent Perception

2021-11-01 · NeurIPS 2021 12 · Yiming Li, Shunli Ren, Pengxiang Wu, Siheng Chen 외

To promote better performance-bandwidth trade-off for multi-agent perception, we propose a novel distilled collaboration graph (DiscoGraph) to model trainable, pose-aware, and adaptive collaboration among agents. Our key…

3D Object DetectionKnowledge Distillationobject-detectionObject Detection

Exploring and Distilling Posterior and Prior Knowledge for Radiology Report Generation

2021-06-13 · CVPR 2021 1 · Fenglin Liu, Xian Wu, Shen Ge, Wei Fan 외

Automatically generating radiology reports can improve current clinical practice in diagnostic radiology. On one hand, it can relieve radiologists from the heavy burden of report writing; On the other hand, it can remind…

Diagnostic

EvoDRC: A Self-Evolving Agentic Framework for Automated DRC Violation Repair

2026-07-22 · Bing-Yue Wu, Chia-Tung Ho, Haoyu Yang, Brucek Khailany 외 arxiv

Design rule check (DRC) closure remains a major bottleneck in advanced-node physical design. Although detailed routers are rule-aware, residual design rule violations (DRVs) often require manual engineering change order …