Coarse-to-Fine Grained Classification
Lists
Only you see this
Abstract
Fine-grained image classification and retrieval become topical in both computer vision and information retrieval. In real-life scenarios, fine-grained tasks tend to appear along with coarse-grained tasks when the observed object is coming closer. However, in previous works, the combination of fine-grained and coarse-grained tasks was often ignored. In this paper, we define a new problem called coarse-to-fine grained classification (C2FGC) which aims to recognize the classes of objects in multiple resolutions (from low to high). To solve this problem, we propose a novel Multi-linear Pooling with Hierarchy (MLPH) model. Specifically, we first design a multi-linear pooling module to include both trilinear and bilinear pooling, and then formulate the coarse-grained and fine-grained tasks within a unified framework. Experiments on two benchmark datasets show that our model achieves state-of-the-art results.
BibTeX
@inproceedings{huo2019coarse,
author = {Yuqi Huo and Yao Lu and Yulei Niu and Zhiwu Lu and Ji-Rong Wen},
title = {{Coarse-to-Fine Grained Classification}},
booktitle = {International ACM SIGIR Conference on Research and Development in Information Retrieval},
year = {2019},
doi = {10.1145/3331184.3331336},
}Loading related content...