CNN: Single-label to Multi-label release_fblygmb4hbfp7ioeznjtcelbk4

by Yunchao Wei, Wei Xia, Junshi Huang, Bingbing Ni, Jian Dong, Yao Zhao, Shuicheng Yan

Released as a article .

2014  

Abstract

Convolutional Neural Network (CNN) has demonstrated promising performance in single-label image classification tasks. However, how CNN best copes with multi-label images still remains an open problem, mainly due to the complex underlying object layouts and insufficient multi-label training images. In this work, we propose a flexible deep CNN infrastructure, called Hypotheses-CNN-Pooling (HCP), where an arbitrary number of object segment hypotheses are taken as the inputs, then a shared CNN is connected with each hypothesis, and finally the CNN output results from different hypotheses are aggregated with max pooling to produce the ultimate multi-label predictions. Some unique characteristics of this flexible deep CNN infrastructure include: 1) no ground truth bounding box information is required for training; 2) the whole HCP infrastructure is robust to possibly noisy and/or redundant hypotheses; 3) no explicit hypothesis label is required; 4) the shared CNN may be well pre-trained with a large-scale single-label image dataset, e.g. ImageNet; and 5) it may naturally output multi-label prediction results. Experimental results on Pascal VOC2007 and VOC2012 multi-label image datasets well demonstrate the superiority of the proposed HCP infrastructure over other state-of-the-arts. In particular, the mAP reaches 84.2% by HCP only and 90.3% after the fusion with our complementary result in [47] based on hand-crafted features on the VOC2012 dataset, which significantly outperforms the state-of-the-arts with a large margin of more than 7%.
In text/plain format

Archived Files and Locations

application/pdf  4.1 MB
file_hnbsbxskvfdhvgotiumskuhcxe
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   accepted
Date   2014-07-09
Version   v3
Language   en ?
arXiv  1406.5726v3
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 3aa6d3db-4b43-4ae3-9fb2-dc4b176f1e99
API URL: JSON