Differentiable Low-computation Global Correlation Loss for Monotonicity Evaluation in Quality Assessment

TL;DR

This paper introduces a differentiable, low-computation loss function for monotonicity evaluation in quality assessment, improving global correlation measurement during training.

Contribution

It presents a novel differentiable SROCC-based loss and a memory bank mechanism to align batch training with global evaluation, enhancing quality assessment accuracy.

Findings

Improved performance on image quality assessment tasks.

Enhanced accuracy in point cloud quality evaluation.

Effective mitigation of batch-global discrepancy issues.

Abstract

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.