Most conventional fine-grained image recognitions are based on a two-stream model of
object-level and part-level CNNs, where the part-level CNN is responsible for learning the …

Fine-grained visual recognition is to classify objects with visually similar appearances into
subcategories, which has made great progress with the development of deep CNNs …

Fine-grained categorization, which aims to distinguish subordinate-level categories such as
bird species or dog breeds, is an extremely challenging task. This is due to two main issues …

Fine-grained image classification is to recognize hundreds of subcategories in each basic-
level category. Existing methods employ discriminative localization to find the key …

Fine-grained classification is challenging because categories can only be discriminated by
subtle and local differences. Variances in the pose, scale or rotation usually make the …

Fine-grained visual classification is a challenging task due to the high similarity between
categories and distinct differences among data within one single category. To address the …

Extracting discriminative fine-grained features is essential for fine-grained image recognition
tasks. Many researchers utilize expensive human annotations to learn discriminative part …

Labeling objects at a subordinate level typically requires expert knowledge, which is not
always available when using random annotators. As such, learning directly from web …

Multi-instance learning (MIL) is widely acknowledged as a fundamental method to solve
weakly supervised problems. While MIL is usually effective in standard weakly supervised …

Fine-grained visual categorization is a classification task for distinguishing categories with
high intra-class and small inter-class variance. While global approaches aim at using the …