Sampled Image Tagging and Retrieval Methods on User Generated Content

Karl Ni, Kyle Zaragoza, Alexander Gude, Yonas Tesfaye, Carmen Carrano, Charles Foster and Barry Chen

Abstract

Traditional image tagging and retrieval algorithms have limited generalizability as a result of being trained with heavily curated datasets. These limitations are most evident when arbitrary search words are used that do not intersect with training set labels. Weak labels from user-generated content (UGC) found in the wild (e.g., Google Photos, FlickR, etc.) have an almost unlimited number of unique words in the metadata tags. Prior work on word embeddings successfully leveraged unstructured text with large vocabularies, and our proposed method seeks to apply similar cost functions to open source imagery. Specifically, we train a deep learning image tagging and retrieval system on large-scale UGC using sampling methods and joint optimization of word embeddings. By using the Yahoo! FlickR Creative Commons (YFCC100M) dataset, such an approach builds robustness to common unstructured data issues that include but are not limited to irrelevant tags, misspellings, multiple languages, polysemy, and tag imbalance.

Session

Spotlights

Files

PDF iconPaper (PDF)
MP4 iconVideo (MP4)

DOI

10.5244/C.31.104
https://dx.doi.org/10.5244/C.31.104

Citation

Karl Ni, Kyle Zaragoza, Alexander Gude, Yonas Tesfaye, Carmen Carrano, Charles Foster and Barry Chen. Sampled Image Tagging and Retrieval Methods on User Generated Content. In T.K. Kim, S. Zafeiriou, G. Brostow and K. Mikolajczyk, editors, Proceedings of the British Machine Vision Conference (BMVC), pages 104.1-104.12. BMVA Press, September 2017.

Bibtex

            @inproceedings{BMVC2017_104,
                title={Sampled Image Tagging and Retrieval Methods on User Generated Content},
                author={Karl Ni, Kyle Zaragoza, Alexander Gude, Yonas Tesfaye, Carmen Carrano, Charles Foster and Barry Chen},
                year={2017},
                month={September},
                pages={104.1-104.12},
                articleno={104},
                numpages={12},
                booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
                publisher={BMVA Press},
                editor={Tae-Kyun Kim, Stefanos Zafeiriou, Gabriel Brostow and Krystian Mikolajczyk},
                doi={10.5244/C.31.104},
                isbn={1-901725-60-X},
                url={https://dx.doi.org/10.5244/C.31.104}
            }