computer-vision-10
Semi-Supervised Sketch Based Image Retrieval
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)
Benchmarks
These leaderboards are used to track progress in semi-supervised-sketch-based-image-retrieval-10
Trend
Dataset
Best Model
Actions
No benchmarks available.
Libraries
iUse these libraries to find semi-supervised-sketch-based-image-retrieval-10 models and implementations
Datasets
No datasets available.
Subtasks
No subtasks available.
Most implemented papers
More Photos are All You Need: Semi-Supervised Learning for Fine-Grained Sketch Based Image Retrieval
T. Xiang, Yongxin Yang, Yi-Zhe Song, Pinaki Nath Chowdhury, A. Bhunia, Aneeshan Sain•Wed Mar 24 2021
This paper introduces a novel semi-supervised framework for cross-modal retrieval that can additionally leverage large-scale unlabelled photos to account for data scarcity, and treats generation and retrieval as two conjugate problems, where a joint learning procedure is devised for each module to mutually benefit from each other.