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.
Krikamol Muandet, Bharath Sriperumbudur, Kenji Fukumizu, Arthur Gretton, and Bernhard Schölkopf
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
dataset 1
citation-polarity summary
roles
dataset 1polarities
use dataset 1representative citing papers
CLP-DD distills small synthetic datasets for linear probing on pre-trained models via closed-form inner solver and discriminative outer loss, matching or exceeding LGM+DSA performance at much lower cost on ImageNet-100 and ImageNet-1K.
AutoBackSwap uses foreground-background disentanglement via a secondary network plus background infilling to augment training data and reduce spurious background correlations in image classifiers, outperforming priors even without any counterexamples in the data.
VaRDASS improves unsupervised domain adaptation by using stratified sampling to reduce variance in discrepancy estimation for measures like correlation alignment and MMD, with derived error bounds, an optimality proof for MMD under assumptions, and a k-means style algorithm.
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.
-
Closed-Form Linear-Probe Dataset Distillation for Pre-trained Vision Models
CLP-DD distills small synthetic datasets for linear probing on pre-trained models via closed-form inner solver and discriminative outer loss, matching or exceeding LGM+DSA performance at much lower cost on ImageNet-100 and ImageNet-1K.
-
Automated Background Swapping for Robustness against Spurious Backgrounds
AutoBackSwap uses foreground-background disentanglement via a secondary network plus background infilling to augment training data and reduce spurious background correlations in image classifiers, outperforming priors even without any counterexamples in the data.
-
Variance Matters: Improving Domain Adaptation via Stratified Sampling
VaRDASS improves unsupervised domain adaptation by using stratified sampling to reduce variance in discrepancy estimation for measures like correlation alignment and MMD, with derived error bounds, an optimality proof for MMD under assumptions, and a k-means style algorithm.