Model Selection for Generalized Zero-shot Learning

In the problem of generalized zero-shot learning, the datapoints from unknown classes are not available during training. The main challenge for generalized zero-shot learning is the unbalanced data distribution which makes it hard for the classifier to distinguish if a given testing sample comes from a seen or unseen class. However, using Generative Adversarial Network (GAN) to generate auxiliary datapoints by the semantic embeddings of unseen classes alleviates the above problem. Current approaches combine the auxiliary datapoints and original training data to train the generalized zero-shot learning model and obtain state-of-the-art results. Inspired by such models, we propose to feed the generated data via a model selection mechanism. Specifically, we leverage two sources of datapoints (observed and auxiliary) to train some classifier to recognize which test datapoints come from seen and which from unseen classes. This way, generalized zero-shot learning can be divided into two disjoint classification tasks, thus reducing the negative influence of the unbalanced data distribution. Our evaluations on four publicly available datasets for generalized zero-shot learning show that our model obtains state-of-the-art results.

[1]  Shaogang Gong,et al.  Semantic Autoencoder for Zero-Shot Learning , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Bernt Schiele,et al.  Feature Generating Networks for Zero-Shot Learning , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[3]  Bernt Schiele,et al.  Evaluation of output embeddings for fine-grained image classification , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[4]  Wei-Lun Chao,et al.  Synthesized Classifiers for Zero-Shot Learning , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[6]  Fatih Murat Porikli,et al.  A Deeper Look at Power Normalizations , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[7]  Bernt Schiele,et al.  Zero-Shot Learning — The Good, the Bad and the Ugly , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Andrew Zisserman,et al.  Automated Flower Classification over a Large Number of Classes , 2008, 2008 Sixth Indian Conference on Computer Vision, Graphics & Image Processing.

[9]  Venkatesh Saligrama,et al.  Zero-Shot Learning via Semantic Similarity Embedding , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[10]  Cordelia Schmid,et al.  Label-Embedding for Attribute-Based Classification , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[11]  Marc'Aurelio Ranzato,et al.  DeViSE: A Deep Visual-Semantic Embedding Model , 2013, NIPS.

[12]  Hongguang Zhang,et al.  Power Normalizing Second-Order Similarity Network for Few-Shot Learning , 2018, 2019 IEEE Winter Conference on Applications of Computer Vision (WACV).

[13]  Philip H. S. Torr,et al.  An embarrassingly simple approach to zero-shot learning , 2015, ICML.

[14]  Rui Zhang,et al.  Museum Exhibit Identification Challenge for the Supervised Domain Adaptation and Beyond , 2018, ECCV.

[15]  Bernt Schiele,et al.  Latent Embeddings for Zero-Shot Classification , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  Christoph H. Lampert,et al.  Attribute-Based Classification for Zero-Shot Visual Object Categorization , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[17]  Hongguang Zhang,et al.  Zero-Shot Kernel Learning , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.