Taming diffusion models for generative segmentation has attracted increasing attention. While existing approaches primarily focus on architectural tweaks or training heuristics, there remains a limited understanding of the intrinsic mismatch between continuous flow matching objectives and discrete perception tasks. In this work, we revisit diffusion segmentation from the perspective of vector field learning. We identify two key limitations of the commonly used flow matching objective: gradient vanishing and trajectory traversing, which result in slow convergence and poor class separation. To tackle these issues, we propose a principled vector field reshaping strategy that augments the learned velocity field with a detached distance-aware correction term. This correction introduces both attractive and repulsive interactions, enhancing gradient magnitudes near centroids while preserving the original diffusion training framework. Furthermore, we design a computationally efficient, quasi-random category encoding scheme inspired by Kronecker sequences, which integrates seamlessly with an end-to-end pixel neural field framework for pixel-level semantic alignment. Extensive experiments consistently demonstrate significant improvements over vanilla flow matching approaches, substantially narrowing the performance gap between generative segmentation and strong discriminative specialists.

翻译：驯服扩散模型用于生成式分割已受到越来越多的关注。尽管现有方法主要关注架构调整或训练启发式策略，但对连续流匹配目标与离散感知任务之间内在不匹配的理解仍十分有限。在本工作中，我们从向量场学习的视角重新审视扩散分割。我们识别出常用流匹配目标的两个关键局限性：梯度消失与轨迹穿越，这导致收敛缓慢与类别分离不佳。为解决这些问题，我们提出了一种原则性的向量场重塑策略，该策略通过一个分离的距离感知修正项来增强学习到的速度场。此修正项同时引入吸引与排斥相互作用，在保持原始扩散训练框架的同时增强质心附近的梯度幅度。进一步地，我们设计了一种受克罗内克序列启发的计算高效准随机类别编码方案，该方案能与端到端像素神经场框架无缝集成，用于像素级语义对齐。大量实验一致表明，与原始流匹配方法相比，该方法取得了显著改进，大幅缩小了生成式分割与强判别式专家之间的性能差距。