3260 papers • 126 benchmarks • 313 datasets
Whilst the number of photos can be easily scaled, each corresponding sketch still needs to be individually produced for fine-grained sketch-based image retrieval. The objective is to mitigate such an upper-bound on sketch data, and study whether unlabelled photos alone (of which they are many) can be cultivated for performance gain.
(Image credit: Papersgraph)
These leaderboards are used to track progress in semi-supervised-sketch-based-image-retrieval-18
No benchmarks available.
Use these libraries to find semi-supervised-sketch-based-image-retrieval-18 models and implementations
No datasets available.
No subtasks available.
Adding a benchmark result helps the community track progress.