3295c76acbf4caaed33c36b1b5fc2cb1-Reviews.html

First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. This paper presents an approach to exploit the local similarity structure for zero-shot or a few-shot problem. The idea is to not only use mid-level representation such as attributes which help in zero-shot problem but also ensure that the unlabeled data is labeled such that similar images receive similar label. Overall, I like the direction of the paper. I think exploiting graph structure is an interesting idea which hasn't been looked into the zero-shot problem (as far as I know).