arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2610.21579cs.LGcs.AIcs.GR
收藏

从已验证程序中学习搜索可执行制版方法

Learning to Search for Executable Patternmaking from Certified Programs

Macau University of Science and Technology(澳门科技大学)

Zhuotao Xu, Chi Zeng, Liying Yang, Xinxing Yu, Yanyan Liang

AI总结:

提出SemDraft框架,从成对前后缝纫制版学习搜索可执行制版程序,经三项检查验证,训练的排序器在1000次搜索内验证更多顺序敏感案例。

摘要:

现有模型可从图像或文本生成缝纫制版,基于程序的表示使这些制版可执行,但这类系统仅生成最终制版,未建模制版师将一种制版转换为另一种的过程。实际中,新款式通过编辑现有制版制成,如加长衣身、移动省道、更换袖子,制版档案仅记录编辑结果,未记录编辑步骤。我们发现可通过搜索编辑动作直至一种制版变为另一种来恢复步骤,确定性编译器可验证恢复步骤。为此,我们提出SemDraft,首个无需记录编辑步骤,从成对的前后缝纫制版中学习搜索可执行制版程序的框架。具体而言,有界搜索恢复编辑动作程序,并通过三项检查验证:从头重新编译、每对动作被分类为有序或可互换、独立重放得到相同制版。已验证程序随后训练模型,对同一搜索内的候选动作排序。在80个顺序敏感案例的两次随机抽取中,固定其他搜索组件,学习得到的排序器在1000次搜索执行内分别验证63和64个案例,而非学习的排序器最多验证53和52个案例。

英文摘要:

Recent models generate sewing patterns from images or text, and program-based representations make these patterns executable. These systems produce a finished pattern and do not model how a patternmaker turns one pattern into another. In practice a new style is made by editing an existing pattern: lengthening the bodice, moving a dart, swapping a sleeve. Pattern archives record the results of such edits and none of the steps. We observe that the steps can be recovered by searching over editing actions until one pattern becomes the other. A deterministic compiler makes the recovered steps checkable. To this end, we present SemDraft, the first framework that learns to search for executable patternmaking programs from paired before-and-after sewing patterns without recorded editing steps. Specifically, a bounded search recovers a program of editing actions and certifies it only after three checks: it recompiles from scratch, every pair of its actions is classified as ordered or interchangeable, and an independent replay reaches the same pattern. The certified programs then train a model that ranks candidate actions inside the same search. On two frozen draws of 80 order-sensitive cases, with every other search component fixed, the learned ranker certifies 63 and 64 cases within 1,000 search executions, against at most 53 and 52 for non-learned rankers.

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。

↑