提出可微分低计算量损失函数，提升质量评估的单调一致性
Differentiable Low-computation Global Correlation Loss for Monotonicity Evaluation in Quality Assessment
- 将斯皮尔曼相关系数直接转为可微损失，避免传统方法间接近似
- 在图像与点云任务中均实现性能提升，验证方法有效性
- 引入记忆库机制，缓解批量训练与全局评估间的偏差
本文提出一种用于质量评估的全局单调一致性训练策略，包含一个可微、低计算量的单调性评估损失函数和全局感知训练机制。与传统排名损失和线性规划方法间接实现斯皮尔曼等级相关系数（SROCC）不同，本方法通过使SROCC中的排序操作可微并可计算，直接将其转化为损失函数。为进一步缓解网络训练中批量优化与SROCC全局评估之间的差异，引入记忆库机制：该机制存储前一批次无梯度的预测结果，并在当前批次训练中使用，以防止梯度突变。在图像与点云质量评估任务上进行评估，结果表明该方法在两类任务中均取得性能提升。
原文摘要 · Abstract (English)
In this paper, we propose a global monotonicity consistency training strategy for quality assessment, which includes a differentiable, low-computation monotonicity evaluation loss function and a global perception training mechanism. Specifically, unlike conventional ranking loss and linear programming approaches that indirectly implement the Spearman rank-order correlation coefficient (SROCC) function, our method directly converts SROCC into a loss function by making the sorting operation within SROCC differentiable and functional. Furthermore, to mitigate the discrepancies between batch optimization during network training and global evaluation of SROCC, we introduce a memory bank mechanism. This mechanism stores gradient-free predicted results from previous batches and uses them in the current batch's training to prevent abrupt gradient changes. We evaluate the performance of the proposed method on both images and point clouds quality assessment tasks, demonstrating performance gains in both cases.
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。