Are You Sure You Want To Do That? Classification with Verification
arXiv:1809.02652
Abstract
Classification systems typically act in isolation, meaning they are required to implicitly memorize the characteristics of all candidate classes in order to classify. The cost of this is increased memory usage and poor sample efficiency. We propose a model which instead verifies using reference images during the classification process, reducing the burden of memorization. The model uses iterative nondifferentiable queries in order to classify an image. We demonstrate that such a model is feasible to train and can match baseline accuracy while being more parameter efficient. However, we show that finding the correct balance between image recognition and verification is essential to pushing the model towards desired behavior, suggesting that a pipeline of recognition followed by verification is a more promising approach.
arXiv comment9 pages, 5 figures, preprint
References in corpus (7)
- Prototypical Networks for Few-shot Learning
- Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
- Categorical Reparameterization with Gumbel-Softmax
- The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables
- Matching Networks for One Shot Learning
- Ask the Right Questions: Active Question Reformulation with Reinforcement Learning
- Teaching Machines to Describe Images via Natural Language Feedback