Header logo is

Learning Transformation Invariant Representations with Weak Supervision

2018

Conference Paper

avg


Deep convolutional neural networks are the current state-of-the-art solution to many computer vision tasks. However, their ability to handle large global and local image transformations is limited. Consequently, extensive data augmentation is often utilized to incorporate prior knowledge about desired invariances to geometric transformations such as rotations or scale changes. In this work, we combine data augmentation with an unsupervised loss which enforces similarity between the predictions of augmented copies of an input sample. Our loss acts as an effective regularizer which facilitates the learning of transformation invariant representations. We investigate the effectiveness of the proposed similarity loss on rotated MNIST and the German Traffic Sign Recognition Benchmark (GTSRB) in the context of different classification models including ladder networks. Our experiments demonstrate improvements with respect to the standard data augmentation approach for supervised and semi-supervised learning tasks, in particular in the presence of little annotated data. In addition, we analyze the performance of the proposed approach with respect to its hyperparameters, including the strength of the regularization as well as the layer where representation similarity is enforced.

Author(s): Benjamin Coors and Alexandru Condurache and Alfred Mertins and Andreas Geiger
Book Title: International Conference on Computer Vision Theory and Applications
Year: 2018

Department(s): Autonomous Vision
Bibtex Type: Conference Paper (inproceedings)
Paper Type: Conference

Event Name: International Conference on Computer Vision Theory and Applications

Links: pdf

BibTex

@inproceedings{Coors2018VISAPP,
  title = {Learning Transformation Invariant Representations with Weak Supervision },
  author = {Coors, Benjamin and Condurache, Alexandru and Mertins, Alfred and Geiger, Andreas},
  booktitle = {International Conference on Computer Vision Theory and Applications},
  year = {2018}
}