AI Paper Atlas

Research map / Label-efficient and robust learning / OOD and anomaly detection

Agree to Disagree: Diversity through Disagreement for Better Transferability

Matteo Pagliardini, Martin Jaggi, François Fleuret, Sai Praneeth Karimireddy

ICLR 2023 · Label-efficient and robust learning › OOD and anomaly detection · approach: Robust fine-tuning for OOD generalization · 7 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Add D-BAT disagreement term on unlabeled OOD data (ensemble of 2) vs ERMLeNet on C-MNIST · C-MNISTtest accuracy: 12.3 -> 90.2Improved
Add D-BAT disagreement term on unlabeled OOD data vs ERMLeNet on M/C-Dominoes · M/C-Dtest accuracy: 50.0 -> 73.3Improved
Add D-BAT disagreement term when D_ood differs from test domain vs ERMLeNet on M/C-Dominoes · M/C-Dtest accuracy: 50.0 -> 58.0Improved
Add D-BAT disagreement term on unlabeled test-like OOD data vs ERMResNet-50 on Waterbirds (single model) · Waterbirdstest accuracy: 86.0 -> 88.7Improved
Add D-BAT disagreement term on Office-Home Art domain vs ERM ensembleResNet-18 on Office-Home · Office-Hometest accuracy: 50.4 -> 51.1 single; 53.9 -> 54.5 ensemble (D_ood≠test)Mixed
Add D-BAT disagreement term on Camelyon17 unlabeled test data vs ERMResNet-50 on Camelyon17 · Camelyon17test accuracy: 80.3 -> 93.1 single; 80.9 -> 91.9 ensembleImproved
Add D-BAT disagreement with out-of-domain unlabeled validation data (Camelyon17)ResNet-50 on Camelyon17 · Camelyon17 (D_ood ≠ test)test accuracy: 80.3 -> 88.8 single; 80.9 -> 85.9 ensembleImproved
Add D-BAT disagreement on OOD samples with CIFAR-10 classes 5-9 (ensemble of 4)modified ResNet-18 on CIFAR-10 uncertainty · CIFAR-10 vs CIFAR-100 OODaverage ensemble accuracy: 92% (deep ensembles) -> 91.2% (D-BAT)Mixed
Add D-BAT disagreement on OOD data for uncertainty (predicted probabilities on OOD samples are lower)CIFAR-10 ensembles · CIFAR-100 test as OODpredicted probability on OOD samplesImproved
Sequential vs simultaneous training of D-BAT ensemble members on 2D toy task (ablation)D-BAT 2D toy · 2D toyqualitative solution simplicityImproved
Add D-BAT disagreement term on ERM baseline with spurious feature perfectly correlated (C-MNIST/dominoes)LeNet ERM baseline · C-MNIST, M/F-D, M/C-Dtest accuracyNo clear effect
Using a larger ensemble size (5) vs 2 for D-BAT (ablation)D-BAT on Waterbirds and Office-Home · Waterbirds, Office-Hometest accuracy vs ensemble sizeNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy