Current approaches for fine-grained recognition do the following: First, recruit experts to annotate a dataset of images, optionally also collecting more structured data in the form of …
We propose a new method for fine-grained object recognition that employs part-level annotations and deep convolutional neural networks (CNNs) in a unified framework …
Recognizing fine-grained sub-categories such as birds and dogs is extremely challenging due to the highly localized and subtle differences in some specific parts. Most previous …
A Angelova, S Zhu - Proceedings of the IEEE conference on …, 2013 - openaccess.thecvf.com
We propose a detection and segmentation algorithm for the purposes of fine-grained recognition. The algorithm first detects low-level regions that could potentially belong to the …
Most convolutional neural networks (CNNs) lack midlevel layers that model semantic parts of objects. This limits CNN-based methods from reaching their full potential in detecting and …
J Krause, T Gebru, J Deng, LJ Li… - 2014 22nd International …, 2014 - ieeexplore.ieee.org
This paper addresses the problem of fine-grained recognition: recognizing subordinate categories such as bird species, car models, or dog breeds. We focus on two major …
Fine-grained classification involves distinguishing between similar sub-categories based on subtle differences in highly localized regions; therefore, accurate localization of …
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 …
Z Huang, Y Li - Proceedings of the IEEE/CVF conference on …, 2020 - openaccess.thecvf.com
We present an interpretable deep model for fine-grained visual recognition. At the core of our method lies the integration of region-based part discovery and attribution within a deep …