Collaboratively Weighting Deep and Classic Representation via $l_2$ Regularization for Image Classification

Shaoning Zeng, Bob Zhang, Yanghao Zhang, Jianping Gou
Proceedings of The 10th Asian Conference on Machine Learning, PMLR 95:502-517, 2018.

Abstract

Deep convolutional neural networks provide a powerful feature learning capability for image classification. The deep image features can be utilized to deal with many image understanding tasks like image classification and object recognition. However, the robustness obtained in one dataset can be hardly reproduced in the other domain, which leads to inefficient models far from state-of-the-art. We propose a deep collaborative weight-based classification (DeepCWC) method to resolve this problem, by providing a novel option to fully take advantage of deep features in classic machine learning. It firstly performs the $l_2$-norm based collaborative representation on the original images, as well as the deep features extracted by deep CNN models. Then, two distance vectors, obtained based on the pair of linear representations, are fused together via a novel collaborative weight. This collaborative weight enables deep and classic representations to weigh each other. We observed the complementarity between two representations in a series of experiments on 10 facial and object datasets. The proposed DeepCWC produces very promising classification results, and outperforms many other benchmark methods, especially the ones claimed for Fashion-MNIST. The code is going to be published in our public repository\footnote{https://github.com/zengsn/research}.

Cite this Paper

BibTeX
@InProceedings{pmlr-v95-zeng18a, title = {Collaboratively Weighting Deep and Classic Representation via $l_2$ Regularization for Image Classification}, author = {Zeng, Shaoning and Zhang, Bob and Zhang, Yanghao and Gou, Jianping}, booktitle = {Proceedings of The 10th Asian Conference on Machine Learning}, pages = {502--517}, year = {2018}, editor = {Zhu, Jun and Takeuchi, Ichiro}, volume = {95}, series = {Proceedings of Machine Learning Research}, month = {14--16 Nov}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v95/zeng18a/zeng18a.pdf}, url = {https://proceedings.mlr.press/v95/zeng18a.html}, abstract = {Deep convolutional neural networks provide a powerful feature learning capability for image classification. The deep image features can be utilized to deal with many image understanding tasks like image classification and object recognition. However, the robustness obtained in one dataset can be hardly reproduced in the other domain, which leads to inefficient models far from state-of-the-art. We propose a deep collaborative weight-based classification (DeepCWC) method to resolve this problem, by providing a novel option to fully take advantage of deep features in classic machine learning. It firstly performs the $l_2$-norm based collaborative representation on the original images, as well as the deep features extracted by deep CNN models. Then, two distance vectors, obtained based on the pair of linear representations, are fused together via a novel collaborative weight. This collaborative weight enables deep and classic representations to weigh each other. We observed the complementarity between two representations in a series of experiments on 10 facial and object datasets. The proposed DeepCWC produces very promising classification results, and outperforms many other benchmark methods, especially the ones claimed for Fashion-MNIST. The code is going to be published in our public repository\footnote{https://github.com/zengsn/research}.} }
Endnote
%0 Conference Paper %T Collaboratively Weighting Deep and Classic Representation via $l_2$ Regularization for Image Classification %A Shaoning Zeng %A Bob Zhang %A Yanghao Zhang %A Jianping Gou %B Proceedings of The 10th Asian Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2018 %E Jun Zhu %E Ichiro Takeuchi %F pmlr-v95-zeng18a %I PMLR %P 502--517 %U https://proceedings.mlr.press/v95/zeng18a.html %V 95 %X Deep convolutional neural networks provide a powerful feature learning capability for image classification. The deep image features can be utilized to deal with many image understanding tasks like image classification and object recognition. However, the robustness obtained in one dataset can be hardly reproduced in the other domain, which leads to inefficient models far from state-of-the-art. We propose a deep collaborative weight-based classification (DeepCWC) method to resolve this problem, by providing a novel option to fully take advantage of deep features in classic machine learning. It firstly performs the $l_2$-norm based collaborative representation on the original images, as well as the deep features extracted by deep CNN models. Then, two distance vectors, obtained based on the pair of linear representations, are fused together via a novel collaborative weight. This collaborative weight enables deep and classic representations to weigh each other. We observed the complementarity between two representations in a series of experiments on 10 facial and object datasets. The proposed DeepCWC produces very promising classification results, and outperforms many other benchmark methods, especially the ones claimed for Fashion-MNIST. The code is going to be published in our public repository\footnote{https://github.com/zengsn/research}.
APA
Zeng, S., Zhang, B., Zhang, Y. & Gou, J.. (2018). Collaboratively Weighting Deep and Classic Representation via $l_2$ Regularization for Image Classification. Proceedings of The 10th Asian Conference on Machine Learning, in Proceedings of Machine Learning Research 95:502-517 Available from https://proceedings.mlr.press/v95/zeng18a.html.

Related Material