判别式
计算机科学
人工智能
模式识别(心理学)
聚类分析
机器学习
特征学习
代表(政治)
上下文图像分类
光学(聚焦)
深度学习
任务(项目管理)
图像(数学)
物理
光学
经济
管理
法学
政治
政治学
作者
Javier Ródenas,Bhalaji Nagarajan,Marc Bolaños,Petia Radeva
标识
DOI:10.1145/3552484.3555754
摘要
Food image recognition is a complex computer vision task, because of the large number of fine-grained food classes. Fine-grained recognition tasks focus on learning subtle discriminative details to distinguish similar classes. In this paper, we introduce a new method to improve the classification of classes that are more difficult to discriminate based on Multi-Subsets learning. Using a pre-trained network, we organize classes in multiple subsets using a clustering technique. Later, we embed these subsets in a multi-head model structure. This structure has three distinguishable parts. First, we use several shared blocks to learn the generalized representation of the data. Second, we use multiple specialized blocks focusing on specific subsets that are difficult to distinguish. Lastly, we use a fully connected layer to weight the different subsets in an end-to-end manner by combining the neuron outputs. We validated our proposed method using two recent state-of-the-art vision transformers on three public food recognition datasets. Our method was successful in learning the confused classes better and we outperformed the state-of-the-art on the three datasets.
科研通智能强力驱动
Strongly Powered by AbleSci AI