DBScholar

Back to papers

GOGGLES: Automatic Image Labeling with Affinity Coding

Summary: GOGGLES introduces affinity coding, a domain-agnostic approach to automatic image labeling using affinity functions to compare instance pairs and separate same-class from different-class pairs. A hierarchical generative model infers labels from a small development set, delivering 71-98% accuracy and outperforming Snuba and few-shot baselines while approaching fully supervised performance. (summarized by gpt-5-nano on Feb 09 2026)

Paper ID
5867
Venue
SIGMOD
Year
2020
Pagerank
6.6952549e-05
Overall Rank
4,451 | 69.47%
DOI
10.1145/3318464.3380592

Incoming Non-self Citations Over Time

Authors

BibTeX Citation

@inproceedings{das_sigmod20,
        title = {{GOGGLES: Automatic Image Labeling with Affinity Coding}},
        author = {Das, Nilaksh and Chaba, Sanya and Wu, Renzhi and Gandhi, Sakshi and Chau, Duen Horng and Chu, Xu},
        series = {{SIGMOD} '20},
        booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
        publisher = {Association for Computing Machinery},
        doi = {10.1145/3318464.3380592},
        url = {https://dl.acm.org/doi/10.1145/3318464.3380592},
        year = {2020}
}

Incoming Citations (Sorted by Pagerank)

Showing 7 of 7 citing papers.

Previous Page 1 / 1 Next

Outgoing Citations (Sorted by Pagerank)

Showing 6 of 6 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Previous Page 1 / 1 Next

Semantically Similar Papers