针对低光图像增强模型冗余问题，提出动态注意力重分配与正交参数生成新方法。
Rethinking Model Redundancy for Low-light Image Enhancement
- 通过动态重分配注意力缓解参数有害性
- 通过正交参数生成防止参数退化
- 适合关注模型效率与性能平衡的研究者
低光图像增强（LLIE）是计算摄影中的基础任务，旨在改善光照、降低噪声并提升图像质量。尽管近期研究多聚焦于设计复杂的神经网络模型，但我们观察到这些模型存在显著冗余，限制了性能进一步提升。本文重新审视LLIE中的模型冗余问题，识别出参数有害性和参数无用性。受此启发，提出两种创新技术：注意力动态重分配（ADR）和参数正交生成（POG）。ADR根据原始注意力动态分配合适注意力，缓解参数有害性；POG学习参数的正交基嵌入，防止参数退化为静态状态，从而缓解参数无用性。实验验证了所提方法的有效性，代码将公开发布。
原文摘要 · Abstract (English)
Low-light image enhancement (LLIE) is a fundamental task in computational photography, aiming to improve illumination, reduce noise, and enhance the image quality of low-light images. While recent advancements primarily focus on customizing complex neural network models, we have observed significant redundancy in these models, limiting further performance improvement. In this paper, we investigate and rethink the model redundancy for LLIE, identifying parameter harmfulness and parameter uselessness. Inspired by the rethinking, we propose two innovative techniques to mitigate model redundancy while improving the LLIE performance: Attention Dynamic Reallocation (ADR) and Parameter Orthogonal Generation (POG). ADR dynamically reallocates appropriate attention based on original attention, thereby mitigating parameter harmfulness. POG learns orthogonal basis embeddings of parameters and prevents degradation to static parameters, thereby mitigating parameter uselessness. Experiments validate the effectiveness of our techniques. We will release the code to the public.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。