# A Feature Embedding Strategy for High-level CNN representations from Multiple ConvNets Source: [A Feature Embedding Strategy for High-level CNN representations from Multiple ConvNets]() Collection index: [llms.txt]() Data updated: 2025-10-25T20:39:15.914Z Authors: Thangarajah Akilan, Q.M. Jonathan Wu, Wei Jiang (2) \_\_INSTITUTION\_3\_\_ Department of Electrical, Computer Engineering, University of Windsor, Canada, (2) Department of Control Science, Engineering, Zhejiang University, China) Published: 2017-05-11T17:38:12.000Z ## 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()