Published on Mon Apr 20 2015

Weakly Supervised Fine-Grained Image Categorization

Yu Zhang, Xiu-shen Wei, Jianxin Wu, Jianfei Cai, Jiangbo Lu, Viet-Anh Nguyen, Minh N. Do

Fine-grained image categorization aims to classify objects with subtle distinctions. Most existing works heavily rely on object / part detectors to build the correspondence between object and part. We propose to select useful parts from multi-scale part proposals and use them to compute a global image representation.

0
0
0
Abstract

In this paper, we categorize fine-grained images without using any object / part annotation neither in the training nor in the testing stage, a step towards making it suitable for deployments. Fine-grained image categorization aims to classify objects with subtle distinctions. Most existing works heavily rely on object / part detectors to build the correspondence between object parts by using object or object part annotations inside training images. The need for expensive object annotations prevents the wide usage of these methods. Instead, we propose to select useful parts from multi-scale part proposals in objects, and use them to compute a global image representation for categorization. This is specially designed for the annotation-free fine-grained categorization task, because useful parts have shown to play an important role in existing annotation-dependent works but accurate part detectors can be hardly acquired. With the proposed image representation, we can further detect and visualize the key (most discriminative) parts in objects of different classes. In the experiment, the proposed annotation-free method achieves better accuracy than that of state-of-the-art annotation-free and most existing annotation-dependent methods on two challenging datasets, which shows that it is not always necessary to use accurate object / part annotations in fine-grained image categorization.

Mon Sep 16 2019
Machine Learning
Classification-Specific Parts for Improving Fine-Grained Visual Categorization
Fine-grained visual categorization is a classification task for high intra-class and small inter-class variance. While global approaches aim at using the whole image, part-based solutions gather additional local information in terms of attentions or parts.
0
0
0
Sat Jun 16 2018
Computer Vision
Part-Aware Fine-grained Object Categorization using Weakly Supervised Part Detection Network
Fine-grained object categorization aims for distinguishing objects of different categories that belong to the same entry-level object category. The task is challenging due to the fact that training images with ground-truth labels are difficult to obtain. In this work, we propose a Weakly Supervised Part Detection Network (PartNet) that is able to detect discriminative local parts.
0
0
0
Tue Feb 26 2019
Computer Vision
Unsupervised Part Mining for Fine-grained Image Classification
Fine-grained image classification remains challenging due to the large intra-class variance. Most existing approaches localize object or parts in an image with object or part annotations, which are expensive and labor-consuming. We propose a fully unsupervised part mining (UPM) approach to
0
0
0
Thu Apr 06 2017
Computer Vision
Object-Part Attention Model for Fine-grained Image Classification
Fine-grained image classification is to recognize hundreds of subcategories belonging to the same basic-level category. Existing methods typically first locate the objects or parts and then discriminate which subcategory the image belongs to.
0
0
0
Thu Feb 04 2021
Computer Vision
Mask guided attention for fine-grained patchy image classification
MGA integrates a pre-trained semantic segmentation model that produces auxiliary supervision signal. The patchy attention mask drives the classifier to filter out the insignificant parts of images. MGA improves the accuracy by 2.25% and 2.2% on
0
0
0
Sat Sep 30 2017
Computer Vision
Fast Fine-grained Image Classification via Weakly Supervised Discriminative Localization
Fine-grained image classification is to recognize hundreds of subcategories in each basic-level category. Existing methods employ discriminative localization to find the key distinctions among subc categories. Discriminative localization relies on region proposal methods, which are time-consuming. Multi-level attention guided localization learning is proposed to localize regions with different focuses automatically.
0
0
0