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 2102.04640cs.IRcs.AI
收藏

对平均精度优化的再思考:在正精度之前只惩罚负精度就足够了

Rethinking the Optimization of Average Precision: Only Penalizing Negative Instances before Positive Ones is Enough

Meituan(美团)

Zhuo Li, Weiqing Min, Jiajun Song, Yaohui Zhu, Liping Kang, Xiaoming Wei, Xiaolin Wei, Shuqiang Jiang

摘要:

在图像检索中,对平均精度(AP)的近似值进行优化已被广泛研究。受限于AP的定义,此类方法考虑在每个正实例之前排序的负实例和正实例两者。然而,我们主张,只在正面实例之前惩罚负面实例就足够了,因为损失只来自这些负面实例。为此,我们提出了一种新的损失,即惩罚负实例前正的(PNP),它可以直接最小化的负实例的数量之前,每个积极的。此外,基于AP的方法采用固定的次优梯度分配策略。因此,我们通过构造损失的导函数,系统地研究了不同的梯度分配解决方案,导致PNP-I具有增加的导函数,PNP-D具有减少的导函数。PNP-I通过为它们分配更大的梯度来更多地关注硬正实例,并试图使所有相关实例更接近。相比之下,《民主国家计划》对这类情况关注较少,并缓慢地加以纠正。对于大多数真实世界的数据,一个类通常包含几个局部聚类。PNP-I盲目地收集这些集群,而PNP-D保持它们原样。因此,PNP-D更优越。在三个标准检索数据集上的实验结果与上述分析一致。广泛的评估表明,PNP-D达到了最先进的性能。代码可在https://github.com/interestingzhuo/PNPloss上获得

英文摘要:

Optimizing the approximation of Average Precision (AP) has been widely studied for image retrieval. Limited by the definition of AP, such methods consider both negative and positive instances ranking before each positive instance. However, we claim that only penalizing negative instances before positive ones is enough, because the loss only comes from these negative instances. To this end, we propose a novel loss, namely Penalizing Negative instances before Positive ones (PNP), which can directly minimize the number of negative instances before each positive one. In addition, AP-based methods adopt a fixed and sub-optimal gradient assignment strategy. Therefore, we systematically investigate different gradient assignment solutions via constructing derivative functions of the loss, resulting in PNP-I with increasing derivative functions and PNP-D with decreasing ones. PNP-I focuses more on the hard positive instances by assigning larger gradients to them and tries to make all relevant instances closer. In contrast, PNP-D pays less attention to such instances and slowly corrects them. For most real-world data, one class usually contains several local clusters. PNP-I blindly gathers these clusters while PNP-D keeps them as they were. Therefore, PNP-D is more superior. Experiments on three standard retrieval datasets show consistent results with the above analysis. Extensive evaluations demonstrate that PNP-D achieves the state-of-the-art performance. Code is available at https://github.com/interestingzhuo/PNPloss

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。

↑