| Autor: |
Tian, Qing, Chanda, Sampath, C, Amit Kumar K, Gray, Douglas |
| Předmět: |
|
| Zdroj: |
Multimedia Tools & Applications; Feb2023, Vol. 82 Issue 5, p7383-7400, 18p |
| Abstrakt: |
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. [ABSTRACT FROM AUTHOR] |
| Databáze: |
Complementary Index |
| Externí odkaz: |
|
Full text from SpringerLink