arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.01183cs.CVcs.LG
收藏

通过课程选择与反课程促进优化上下文纠缠内容分割

Refining Context-Entangled Content Segmentation via Curriculum Selection and Anti-Curriculum Promotion

Duke University(杜克大学);Adobe(Adobe公司)

Chunming He, Rihan Zhang, Fengyang Xiao, Dingming Zhang, Zhiwen Cao, Sina Farsiu

AI总结:

提出CurriSeg双阶段学习框架,结合课程学习与反课程学习原理,通过动态数据选择与频谱盲性微调提升上下文纠缠内容分割的鲁棒性和泛化能力。

摘要:

生物学习从简单到困难的任务逐步进行,逐渐增强感知和鲁棒性。受此原理启发,我们解决上下文纠缠内容分割(CECS)这一具有挑战性的场景,其中对象与周围环境共享内在视觉模式,如伪装目标检测。传统分割网络主要依赖架构增强,但往往忽略了在纠缠数据分布下控制鲁棒性的学习动态。我们引入CurriSeg,一个双阶段学习框架,统一了课程和反课程原则以提高表示可靠性。在课程选择阶段,CurriSeg基于样本损失的时间统计动态选择训练数据,区分困难但有信息的样本与噪声或模糊样本,从而实现稳定的能力增强。在反课程促进阶段,我们设计了频谱盲性微调,抑制高频成分以强制依赖低频结构和上下文线索,从而增强泛化能力。大量实验表明,CurriSeg在多种CECS基准上取得了一致的改进,无需增加参数或增加总训练时间,为进展与挑战如何相互作用以促进鲁棒且上下文感知的分割提供了原则性视角。代码将发布。

英文摘要:

Biological learning proceeds from easy to difficult tasks, gradually reinforcing perception and robustness. Inspired by this principle, we address Context-Entangled Content Segmentation (CECS), a challenging setting where objects share intrinsic visual patterns with their surroundings, as in camouflaged object detection. Conventional segmentation networks predominantly rely on architectural enhancements but often ignore the learning dynamics that govern robustness under entangled data distributions. We introduce CurriSeg, a dual-phase learning framework that unifies curriculum and anti-curriculum principles to improve representation reliability. In the Curriculum Selection phase, CurriSeg dynamically selects training data based on the temporal statistics of sample losses, distinguishing hard-but-informative samples from noisy or ambiguous ones, thus enabling stable capability enhancement. In the Anti-Curriculum Promotion phase, we design Spectral-Blindness Fine-Tuning, which suppresses high-frequency components to enforce dependence on low-frequency structural and contextual cues and thus strengthens generalization. Extensive experiments demonstrate that CurriSeg achieves consistent improvements across diverse CECS benchmarks without adding parameters or increasing total training time, offering a principled view of how progression and challenge interplay to foster robust and context-aware segmentation. Code will be released.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑