Gradient Knows Best: Mixed-Precision Quantization via Gradient-Guided Bit Allocation for Super-Resolution
Jun Young Kim, Joo Hyeon Jeon, Sangyeon Ahn, Yoonseo Park, Yong Seok Oh, Bogyeong Kim, Sung In Cho
2026年份
摘要
Although deep learning-based image super-resolution (SR) models have achieved remarkable progress in reconstruction quality, their high computational and memory demands make them unsuitable for lightweight platforms. To
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
它引用的顶会 Paper8
- OMPQ: Orthogonal Mixed Precision QuantizationYuexiao Ma, Taisong Jin, Xiawu Zheng, Yan Wang 等AAAI 2023 · 被引用 56 次
- 2DQuant: Low-bit Post-Training Quantization for Image Super-ResolutionKai Liu, Haotong Qin, Yong Guo, Xin Yuan 等NeurIPS 2024 · 被引用 24 次
- MetaMix: Meta-State Precision Searcher for Mixed-Precision Activation QuantizationHan-Byul Kim, Joo Hyung Lee, Sungjoo Yoo, Hong-Seok KimAAAI 2024 · 被引用 10 次
- Outlier-Aware Post-Training Quantization for Image Super-ResolutionHailing Wang, Jianglin Lu, Yitian Zhang, Yun FuICCV 2025 · 被引用 2 次
- Achieving Lightweight Super-Resolution for Real-Time Computer GraphicsYu Wen, Chen Zhang, Chenhao Xie, Xin FuAAAI 2025 · 被引用 1 次
相关 Paper
- Self-feature Learning: An Efficient Deep Lightweight Network for Image Super-resolutionJun Xiao, Qian Ye, Rui Zhao, Kin-Man Lam 等ACM MM 2021 · 被引用 17 次
- SplitSR: An End-to-End Approach to Super-Resolution on Mobile DevicesXin Liu, Yuang Li, Josh Fromm, Yuntao Wang 等UbiComp 2021 · 被引用 29 次
- Practical Single-Image Super-Resolution Using Look-Up TableYounghyun Jo, Seon Joo KimCVPR 2021
- Towards Lighter and Faster: Learning Wavelets Progressively for Image Super-ResolutionHuanrong Zhang, Zhi Jin, Xiaojun Tan, Xiying LiACM MM 2020 · 被引用 22 次
- Boosting Lightweight Single Image Super-resolution via Joint-distillationXiaotong Luo, Qiuyuan Liang, Ding Liu, Yanyun QuACM MM 2021 · 被引用 9 次
