计算机科学
粒度
人工智能
水准点(测量)
块(置换群论)
卷积(计算机科学)
班级(哲学)
钥匙(锁)
机器学习
对象(语法)
可视化
人工神经网络
模式识别(心理学)
操作系统
地理
几何学
计算机安全
数学
大地测量学
作者
Ruoyi Du,Jiyang Xie,Zhanyu Ma,Dongliang Chang,Yi-Zhe Song,Jun Guo
标识
DOI:10.1109/tpami.2021.3126668
摘要
Fine-grained visual classification (FGVC) is much more challenging than traditional classification tasks due to the inherently subtle intra-class object variations. Recent works are mainly part-driven (either explicitly or implicitly), with the assumption that fine-grained information naturally rests within the parts. In this paper, we take a different stance, and show that part operations are not strictly necessary - the key lies with encouraging the network to learn at different granularities and progressively fusing multi-granularity features together. In particular, we propose: (i) a progressive training strategy that effectively fuses features from different granularities, and (ii) a consistent block convolution that encourages the network to learn the category-consistent features at specific granularities. We evaluate on several standard FGVC benchmark datasets, and demonstrate the proposed method consistently outperforms existing alternatives or delivers competitive results. Codes are available at https://github.com/PRIS-CV/PMG-V2.
科研通智能强力驱动
Strongly Powered by AbleSci AI