Abstract
In text-based person search endeavors, data generation has emerged as a prevailing practice, addressing concerns over privacy preservation and the arduous task of manual annotation. Although the number of synthesized data can be infinite in theory, the scientific conundrum persists that how much generated data optimally fuels subsequent model training. We observe that only a subset of the data in these constructed datasets plays a decisive role. Therefore, we introduce a new Filtering-WoRA paradigm, which contains a filtering algorithm to identify this crucial data subset and WoRA (Weighted Low-Rank Adaptation) learning strategy for light fine-tuning. The filtering algorithm is based on the cross-modality relevance to remove the lots of coarse matching synthesis pairs. As the number of data decreases, we do not need to fine-tune the entire model. Therefore, we propose a WoRA learning strategy to efficiently update a minimal portion of model parameters. WoRA streamlines the learning process, enabling heightened efficiency in extracting knowledge from fewer, yet potent, data instances. Extensive experimentation validates the efficacy of pretraining, where our model achieves advanced and efficient retrieval performance on challenging real-world benchmarks. Notably, on the CUHK-PEDES dataset, we have achieved a competitive mAP of 67.02% while reducing model training time by 19.82%.
Abstract (translated)
在基于文本的人搜索任务中,数据生成已成为一种普遍的做法,解决了隐私保护问题和手动注释的困难任务。虽然在理论上合成数据的数量是无限的,但科学问题仍然存在,那就是生成的数据如何最好地推动后续模型的训练。我们观察到,这些构建数据中只有部分数据对决定性的作用。因此,我们引入了一个新的Filter-WoRA范式,其中包含一个用于确定关键数据子集的过滤算法和用于轻量级微调的WoRA学习策略。过滤算法基于跨模态相关性来删除大量的粗匹配合成对。随着数据量的减少,我们无需对整个模型进行微调。因此,我们提出了一个WoRA学习策略,以有效地更新模型的最小参数部分。WoRA加速了学习过程,使得从更少的、 yet强大的数据实例中提取知识更加高效。大量实验证实了预训练的有效性,我们的模型在具有挑战性的真实世界基准测试中实现了先进的效率和效率。值得注意的是,在CUHK-PEDES数据集上,我们在获得67.02%的竞争mAP的同时将模型训练时间减少了19.82%。
URL
https://arxiv.org/abs/2404.10292