Scaling up fine-grained recognition to all domains of fine-grained objects is a challenge the
computer vision community will need to face in order to realize its goal of recognizing all …

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 …

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 …

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 …

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 …