基于MaskR-CNN上不同犬种的分类分割性能对比分析
摘要
并学习大量的特性来表示每个目标物体的细节。而狗狗数据图片中,狗的种类特征之间(比如毛色,纹理,体型)存在相异性和相似性。所以在本文中,笔者选取并自己制作了两个不同狗类数据集,分别代表特征具有较大相异性和相似性的目标。用这两个狗类数据集来进行MaskR-CNN目标检测性能与实例分割性能的对比分析。
关键词
全文:
PDF参考
[1]Aditya Khosla, Nityananda Jayadevaprakash, Bangpeng Yao and Li Fei-Fei. Novel dataset for Fine-Grained Image Categori- zation. First Workshop on Fine-Grained Visual Categorization (FGVC), IEEE Conference on Computer Vision and Pattern Rec- ognition (CVPR), 2011.
[2]T.-Y. Lin, P. Doll´ar, R. Girshick, K. He, B. Hariharan, and S. Belongie. Feature pyramid networks for object detection. In CVPR, 2017.
[3]K. He, G. Gkioxari, P. Doll´ar, and R. Girshick. Mask r-cnn. In ICCV, 2017.
[4]S. Ren, K. He, R. Girshick, and J. Sun. Faster R-CNN: Towards real-time object detection with region proposal networks. In NIPS, 2015.
[5]J. Long, E. Shelhamer, and T. Darrell. Fully convolutional net- works for semantic segmentation. InCVPR,2015.
[6] Yang L , Song Q , Wang Z , et al. Parsing R-CNN for In- stance-Level Human Analysis[J]. 2018.
DOI: http://dx.doi.org/10.18686/jsjxt.v2i4.30236
Refbacks
- 当前没有refback。