Fine-grained visual classification (FGVC) is much more challenging than traditional classification tasks due to the inherently subtle intra-class object variations. Recent works …
H Sun, X He, Y Peng - Proceedings of the 30th ACM International …, 2022 - dl.acm.org
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 …
JW Cho, DJ Kim, Y Jung… - IEEE transactions on …, 2022 - ieeexplore.ieee.org
Recent state-of-the-art active learning methods have mostly leveraged generative adversarial networks (GANs) for sample acquisition; however, GAN is usually known to …
J Chen, P Wang, J Liu, Y Qian - Proceedings of the IEEE …, 2022 - openaccess.thecvf.com
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 …
R Du, D Chang, K Liang… - Proceedings of the …, 2023 - openaccess.thecvf.com
Although machines have surpassed humans on visual recognition problems, they are still limited to providing closed-set answers. Unlike machines, humans can cognize novel …