Fast Image Tagging Fast Image Tagging
Paper summary Idea: - Fast: simply a linear projection from image feature to semantic tag: learn linear projection **W**. Especially, in testing time, it is almost O(1) complexity compared with the nearest neighbor methods with at least O(N) complexity. - Enrich incomplete tags: learn tag enrichment projection **B** that turns on likely co-occurring tags with existing ones. Marginalized blank-out regularization - Assume observed tags are corrupted, approximate the unknown corrupting distribution with piecewise uniform distribution. - Stacking: multi-layer linear projection. Reconstruct tags that do not co-occur together but tend to appear within similar contexts. - Rare tags and Non-Uniform Corruption: only optimize tags that have recall below some threshold in the validation set.

Summary by Yin Xia 3 years ago
Your comment: allows researchers to publish paper summaries that are voted on and ranked!

Sponsored by: and