Towards semantic knowledge propagation from text corpus to web images

In this paper, we study the problem of transfer learning from text to images in the context of network data in which link based bridges are available to transfer the knowledge between the different domains. The problem of classification of image data is often much more challenging than text data because of the following two reasons: (a) Labeled text data is very widely available for classification purposes. On the other hand, this is often not the case for image data, in which a lot of images are available from many sources, but many of them are often not labeled. (b) The image features are not directly related to semantic concepts inherent in class labels. On the other hand, since text data tends to have natural semantic interpretability (because of their human origins), they are often more directly related to class labels. Therefore, the relationships between the images and text features also provide additional hints for the classification process in terms of the image feature transformations which provide the most effective results. The semantic challenges of image features are glaringly evident, when we attempt to recognize complex abstract concepts, and the visual features often fail to discriminate such concepts. However, the copious availability of bridging relationships between text and images in the context of web and social network data can be used in order to design for effective classifiers for image data. One of our goals in this paper is to develop a mathematical model for the functional relationships between text and image features, so as indirectly transfer semantic knowledge through feature transformations. This feature transformation is accomplished by mapping instances from different domains into a common space of unspecific topics. This is used as a bridge to semantically connect the two heterogeneous spaces. This is also helpful for the cases where little image data is available for the classification process. We evaluate our knowledge transfer techniques on an image classification task with labeled text corpora and show the effectiveness with respect to competing algorithms.

[1]  Qiang Yang,et al.  Translated Learning: Transfer Learning across Different Feature Spaces , 2008, NIPS.

[2]  Michael I. Jordan,et al.  Multiple kernel learning, conic duality, and the SMO algorithm , 2004, ICML.

[3]  Stephen P. Boyd,et al.  Convex Optimization , 2004, Algorithms and Theory of Computation Handbook.

[4]  S. Yun,et al.  An accelerated proximal gradient algorithm for nuclear norm regularized linear least squares problems , 2009 .

[5]  Tommi S. Jaakkola,et al.  Maximum-Margin Matrix Factorization , 2004, NIPS.

[6]  Rajat Raina,et al.  Self-taught learning: transfer learning from unlabeled data , 2007, ICML '07.

[7]  Rajat Raina,et al.  Constructing informative priors using transfer learning , 2006, ICML.

[8]  Michael I. Jordan,et al.  Latent Dirichlet Allocation , 2001, J. Mach. Learn. Res..

[9]  Xian-Sheng Hua,et al.  Learning semantic distance from community-tagged media collection , 2009, MM '09.

[10]  Shimon Ullman,et al.  Uncovering shared structures in multiclass classification , 2007, ICML '07.

[11]  Thomas Hofmann,et al.  Probabilistic Latent Semantic Analysis , 1999, UAI.

[12]  S. Yun,et al.  An accelerated proximal gradient algorithm for nuclear norm regularized linear least squares problems , 2009 .

[13]  Qiang Yang,et al.  Heterogeneous Transfer Learning for Image Clustering via the SocialWeb , 2009, ACL.

[14]  Matthijs C. Dorst.  Distinctive Image Features from Scale-Invariant Keypoints , 2011 .

[15]  Thomas G. Dietterich,et al.  Improving SVM accuracy by training on auxiliary data sources , 2004, ICML.

[16]  Peter W. Foltz,et al.  An introduction to latent semantic analysis , 1998 .

[17]  Emmanuel J. Candès,et al.  A Singular Value Thresholding Algorithm for Matrix Completion , 2008, SIAM J. Optim..

[18]  Qiang Yang,et al.  Heterogeneous Transfer Learning for Image Classification , 2011, AAAI.

[19]  Avrim Blum,et al.  The Bottleneck , 2021, Monopsony Capitalism.