Fast Zero-Shot Image Tagging
This work addresses efficient and versatile image annotation, including zero-shot tagging, but is incremental as it builds on existing word vector and neural network methods.
The paper tackles the problem of image tagging by estimating a principal direction in word vector space to rank relevant tags, achieving superior performance on the NUS-WIDE dataset and outperforming baselines for unseen tags.
The well-known word analogy experiments show that the recent word vectors capture fine-grained linguistic regularities in words by linear vector offsets, but it is unclear how well the simple vector offsets can encode visual regularities over words. We study a particular image-word relevance relation in this paper. Our results show that the word vectors of relevant tags for a given image rank ahead of the irrelevant tags, along a principal direction in the word vector space. Inspired by this observation, we propose to solve image tagging by estimating the principal direction for an image. Particularly, we exploit linear mappings and nonlinear deep neural networks to approximate the principal direction from an input image. We arrive at a quite versatile tagging model. It runs fast given a test image, in constant time w.r.t.\ the training set size. It not only gives superior performance for the conventional tagging task on the NUS-WIDE dataset, but also outperforms competitive baselines on annotating images with previously unseen tags