Improving apparel detection with category grouping and multi-grained branches
Improving apparel detection with category grouping and multi-grained branches
复制标题
DOI：
10.1007/s11042-022-13424-8
复制
发表时间：
2021-01
影响因子：
3.6
通讯作者：
Qing Tian;Sampath Chanda;K. Kumar;Douglas Gray
中科院分区：
文献类型：
--
作者：
Qing Tian;Sampath Chanda;K. Kumar;Douglas Gray
训练一个准确的物体检测器是昂贵和耗时的。一个主要原因在于费力的标记过程，即，注释每个图像中所有实例的类别和边界框信息。在本文中，我们研究了在没有额外标记的情况下提高深度对象检测器性能的方法。我们首先探索将具有高度视觉和语义相似性的现有类别组合在一起作为一个超类别（或超类）。然后，我们研究了如何利用这种层次类别的知识来使用多粒度RCNN分支更好地检测对象。在DeepFashion 2和OpenImagesV 4-Clothing上的实验结果表明，所提出的具有多粒度分支的检测头可以将整体性能提高高达2%，而无需额外耗时的注释。此外，具有较少训练样本的类往往从所提出的具有超类分组的多粒度头部中受益更多。特别是，我们在DeepFashion 2和OpenImagesV 4-Clothing上分别将最后30%类别（就训练样本数量而言）的mAP提高了2.6%和4.6%。
Training an accurate object detector is expensive and time-consuming. One main reason lies in the laborious labeling process, i.e., annotating category and bounding box information for all instances in every image. In this paper, we examine ways to improve performance of deep object detectors without extra labeling. We first explore to group existing categories of high visual and semantic similarities together as one super category (or, a superclass). Then, we study how this knowledge of hierarchical categories can be exploited to better detect objects using multi-grained RCNN branches∗. Experimental results on DeepFashion2 and OpenImagesV4-Clothing reveal that the proposed detection heads with multi-grained branches can boost the overall performance by as high as 2% with no additional time-consuming annotations. In addition, classes that have fewer training samples tend to benefit more from the proposed multi-grained heads with superclass grouping. In particular, we improve the mAP for the last 30% categories (in terms of training sample number) by 2.6% and 4.6% on DeepFashion2 and OpenImagesV4-Clothing, respectively.