ContextShift benchmark on COCO reveals up to 227% more false negatives and 44% fewer predictions under controlled context changes, non-monotonic NPMI response, and gains from context-aware augmentation.
Clad: A contrastive learning based approach for background debiasing.arXiv preprint arXiv:2210.02748, 2022
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
ContextShift: A Controlled Benchmark for Context Dependence in Object Detection
ContextShift benchmark on COCO reveals up to 227% more false negatives and 44% fewer predictions under controlled context changes, non-monotonic NPMI response, and gains from context-aware augmentation.