GAL selects images for user labeling by the estimated impact of each candidate on the retrieval classifier, using a greedy batch scheme, and reports improved retrieval accuracy over prior active learning methods on four benchmarks.
Active learning for imbalanced datasets
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Active Learning via Classifier Impact and Greedy Selection for Interactive Image Retrieval
GAL selects images for user labeling by the estimated impact of each candidate on the retrieval classifier, using a greedy batch scheme, and reports improved retrieval accuracy over prior active learning methods on four benchmarks.