图像分割中条件独立假设的松弛

中文摘要 AI 辅助

在语义分割中，近期一系列RankSEG方法在推理时直接优化Dice/IoU分数，从而在不修改模型训练的情况下提高与评估指标的一致性。尽管这些方法在理论和实证上取得了成功，但RankSEG依赖于限制性的条件独立假设（CIA），该假设忽略了关键的标签相关性，因此在模糊或低对比度场景下性能下降。然而，考虑完整的标签依赖性在计算上不可行，需要$\mathcal{O}(d^3)$的时间复杂度。为解决这一问题，我们将CIA替换为一种空间局部依赖性（SLD）结构，该结构在保持依赖模型可处理的同时捕获局部标签相关性。我们进一步通过互反矩近似结合一种新颖的定点优化策略来克服剩余的计算瓶颈，该策略消除了穷举搜索。所提出的算法实现了高度实用的$\mathcal{O}(d \log d)$复杂度，并在多个分割基准上持续优于传统的argmax和基于CIA的RankSEG方法。在低对比度或小目标场景中，改进显著，其中标签依赖性为准确分割提供了与图像信息互补的有价值信号。实验代码可在该https URL获取。

英文摘要

In semantic segmentation, a recent line of RankSEG methods directly optimizes Dice/IoU scores at inference time, improving alignment with evaluation metrics without modifying model training. Despite its theoretical and empirical success, RankSEG relies on the restrictive Conditional Independence Assumption (CIA), which ignores crucial label correlations and therefore degrades performance in ambiguous or low-contrast scenarios. However, accounting for full label dependence is computationally prohibitive, requiring $\mathcal{O}(d^3)$ time. To address this, we replace the CIA with a Spatially Localized Dependence (SLD) structure that captures local label correlations while keeping the dependence model tractable. We further overcome the remaining computational bottleneck via a Reciprocal Moment Approximation coupled with a novel fixed-point optimization strategy that eliminates exhaustive search. The proposed algorithm achieves a highly practical $\mathcal{O}(d \log d)$ complexity and consistently outperforms conventional argmax and CIA-based RankSEG across diverse segmentation benchmarks. Improvements are significant in low-contrast or small-object scenarios, where label dependence offers valuable signals complementary to image information for accurate segmentation. The code of experiments is available at https://github.com/ZixunWang/RankSEG-DEP.

发表机构

• The Chinese University of Hong Kong（香港中文大学）

机构由 AI 辅助整理，请以论文原文为准。