摘要细粒度图像分类问题是计算机视觉领域一项极具挑战的研究课题, 其目标是对子类进行识别
, 如区分不同种类的鸟. 由于子类别间细微的类间差异和较大的类内差异, 传统的分类算法不得不 …

Recognizing fine-grained categories (eg, bird species) is difficult due to the challenges of
discriminative region localization and fine-grained feature learning. Existing approaches …

Recognizing fine-grained categories (eg, bird species) highly relies on discriminative part
localization and part-based fine-grained feature learning. Existing approaches …

In this paper, we present a novel approach, called Deep MANTA (Deep Many-Tasks), for
many-task vehicle analysis from a given image. A robust convolutional network is introduced …

Fine-grained image classification is to recognize hundreds of subcategories belonging to
the same basic-level category, such as 200 subcategories belonging to the bird, which is …

Pooling second-order local feature statistics to form a high-dimensional bilinear feature has
been shown to achieve state-of-the-art performance on a variety of fine-grained …

Abstract Convolutional Neural Networks (CNNs) with Bilinear Pooling, initially in their full
form and later using compact representations, have yielded impressive performance gains …

Bilinear pooling of Convolutional Neural Network (CNN) features [22, 23], and their compact
variants [10], have been shown to be effective at fine-grained recognition, scene …

We present a simple and effective architecture for fine-grained recognition called Bilinear
Convolutional Neural Networks (B-CNNs). These networks represent an image as a pooled …

Automated Vehicle Classification (AVC) based on vision sensors has received active
attention from researchers, due to heightened security concerns in Intelligent Transportation …