计算机科学
人工智能
一致性(知识库)
机器学习
分类器(UML)
等级制度
特征(语言学)
模式识别(心理学)
利用
编码
语言学
哲学
生物化学
化学
计算机安全
经济
市场经济
基因
作者
Rui Wang,C.L. Zou,Weizhong Zhang,Zixuan Zhu,Lihua Jing
标识
DOI:10.1145/3581783.3612234
摘要
Hierarchical Fine-Grained Visual Classification (HFGVC) assigns a label sequence (e.g., ["Albatross'', "Laysan Albatross'']) with a coarse to fine hierarchy to each object. It remains challenging to achieve high accuracy and consistency due to the small inter-class difference, large intra-class variance, and difficulty in modeling relationships among classification tasks at different granularities. In this paper, we propose an effective Consistency-Aware Feature Learning (CAFL) method for HFGVC to improve prediction consistency and classification accuracy simultaneously. Our key idea is to encode the prediction consistency constraint into a weak supervision mechanism via forward deduction and backward induction over the label hierarchy. Furthermore, we develop a disentanglement and bidirectional reinforcement classification head to extract the features for the classifiers at different granularities. Together with the stop-gradient policy and attention mechanism, they enable each classifier to exploit the features from the ones at other granularities without suffering from their conflicting gradients in training. We evaluate our method on several commonly-used fine-grained public datasets, including CUB-200-2011, FGVC-Aircraft, and Stanford Cars. The results show that our method not only achieves state-of-the-art classification accuracy but also effectively reduces inconsistency errors by 50% under the hierarchical fine-grained classification setting.
科研通智能强力驱动
Strongly Powered by AbleSci AI