Fine-grained image analysis (FGIA) is a longstanding and fundamental problem in computer
vision and pattern recognition, and underpins a diverse set of real-world applications. The …

Fine-grained visual classification (FGVC) is much more challenging than traditional
classification tasks due to the inherently subtle intra-class object variations. Recent works …

Fine-grained visual categorization (FGVC) aims at recognizing objects from similar
subordinate categories, which is challenging and practical for human's accurate automatic …

In recent years, there has been an increasing interest in exploiting logically specified
background knowledge in order to obtain neural models (i) with a better performance,(ii) …

Neural networks (NNs) and decision trees (DTs) are both popular models of machine
learning, yet coming with mutually exclusive advantages and limitations. To bring the best of …

Over the past few years, a significant progress has been made in deep convolutional neural
networks (CNNs)-based image recognition. This is mainly due to the strong ability of such …

Recent state-of-the-art active learning methods have mostly leveraged generative
adversarial networks (GANs) for sample acquisition; however, GAN is usually known to …

Hierarchical multi-granularity classification (HMC) assigns hierarchical multi-granularity
labels to each object and focuses on encoding the label hierarchy, eg,[" Albatross"," Laysan …

Object categories are often grouped into a multi-granularity taxonomic hierarchy. Classifying
objects at coarser-grained hierarchy requires global and common characteristics, while finer …

Although machines have surpassed humans on visual recognition problems, they are still
limited to providing closed-set answers. Unlike machines, humans can cognize novel …