Export Reviews, Discussions, Author Feedback and Meta-Reviews

"NIPS Neural Information Processing Systems 8-11th December 2014, Montreal, Canada",,, "Paper ID:","1807" "Title:","Zero-shot recognition with unreliable attributes" Current Reviews First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. The paper strives to bridge the gap between the theory and practice of attribute-based zero-shot learning. The theory is that novel classes can be recognized automatically using pre-trained attribute predictors; in practice, however, learning these attribute classifiers can be as difficult or even more so than learning the object classes themselves. Random forests are trained to predict unseen classes from attribute vectors, and the training procedure takes into account the reliability of the attribute detectors by propagating a validation set through each decision tree at training time. The authors show how the method can be extended to handle training with a few training examples of test categories.