English

A Feature Embedding Strategy for High-level CNN representations from Multiple ConvNets

Computer Vision and Pattern Recognition 2017-05-12 v1

Abstract

Following the rapidly growing digital image usage, automatic image categorization has become preeminent research area. It has broaden and adopted many algorithms from time to time, whereby multi-feature (generally, hand-engineered features) based image characterization comes handy to improve accuracy. Recently, in machine learning, pre-trained deep convolutional neural networks (DCNNs or ConvNets) have been that the features extracted through such DCNN can improve classification accuracy. Thence, in this paper, we further investigate a feature embedding strategy to exploit cues from multiple DCNNs. We derive a generalized feature space by embedding three different DCNN bottleneck features with weights respect to their Softmax cross-entropy loss. Test outcomes on six different object classification data-sets and an action classification data-set show that regardless of variation in image statistics and tasks the proposed multi-DCNN bottleneck feature fusion is well suited to image classification tasks and an effective complement of DCNN. The comparisons to existing fusion-based image classification approaches prove that the proposed method surmounts the state-of-the-art methods and produces competitive results with fully trained DCNNs as well.

Keywords

Cite

@article{arxiv.1705.04301,
  title  = {A Feature Embedding Strategy for High-level CNN representations from Multiple ConvNets},
  author = {Thangarajah Akilan and Q. M. Jonathan Wu and Wei Jiang},
  journal= {arXiv preprint arXiv:1705.04301},
  year   = {2017}
}

Comments

5 pages, 4 figures

R2 v1 2026-06-22T19:44:27.038Z