Supplementary Material for : Learning More Universal Representations for Transfer-Learning

This supplementary material of our main paper contain the following: (i) a comparison of our methods to the state-of-the-art according all the universality evaluation-metrics of the literature (Sec. 1); (ii) an evaluation of the impact of more and different grouping SPVs used in our MulDiP-Net (Sec. 2); and (iii) the evaluation of MulDiP-Net with more training data and deeper architectures (Sec. 3).

[1]  Dennis Koelma,et al.  The ImageNet Shuffle: Reorganized Pre-training for Video Event Detection , 2016, ICMR.

[2]  Christopher Joseph Pal,et al.  Learning General Purpose Distributed Sentence Representations via Large Scale Multi-task Learning , 2018, ICLR.

[3]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[4]  Hervé Le Borgne,et al.  AMECON: Abstract Meta-Concept Features for Text-Illustration , 2017, ICMR.

[5]  Andrea Vedaldi,et al.  Universal representations: The missing link between faces, text, planktons, and cat breeds , 2017, ArXiv.

[6]  Bolei Zhou,et al.  Learning Deep Features for Scene Recognition using Places Database , 2014, NIPS.

[7]  Adrian Popescu,et al.  Vision-language integration using constrained local semantic features , 2017, Comput. Vis. Image Underst..

[8]  Céline Hudelot,et al.  MuCaLe-Net: Multi Categorical-Level Networks to Generate More Discriminating Features , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[9]  Alexei A. Efros,et al.  What makes ImageNet good for transfer learning? , 2016, ArXiv.

[10]  Andrea Vedaldi,et al.  Efficient Parametrization of Multi-domain Deep Neural Networks , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[11]  Atsuto Maki,et al.  Factors of Transferability for a Generic ConvNet Representation , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[12]  Andrea Vedaldi,et al.  Learning multiple visual domains with residual adapters , 2017, NIPS.

[13]  Jun Li,et al.  Deep Convolutional Neural Network with Independent Softmax for Large Scale Face Recognition , 2016, ACM Multimedia.

[14]  Martial Hebert,et al.  Growing a Brain: Fine-Tuning by Increasing Model Capacity , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).