Deep classifiers are known to rely on spurious features—patterns which are correlated with the target on the training data but not inherently relevant to the learning problem, such as the …
J Liu, T Wang, P Cui… - Advances in Neural …, 2024 - proceedings.neurips.cc
Different distribution shifts require different algorithmic and operational interventions. Methodological research must be grounded by the specific shifts they address. Although …
Abstract Machine learning models have been found to learn shortcuts---unintended decision rules that are unable to generalize---undermining models' reliability. Previous works address …
K Tang, M Tao, J Qi, Z Liu, H Zhang - European Conference on Computer …, 2022 - Springer
Existing long-tailed classification (LT) methods only focus on tackling the class-wise imbalance that head classes have more samples than tail classes, but overlook the attribute …
Machine learning models often perform poorly on subgroups that are underrepresented in the training data. Yet, little is understood on the variation in mechanisms that cause …
Machine learning systems are known to be sensitive to spurious correlations between biased features of the inputs (eg, background, texture, and secondary objects) and the …
T LaBonte, V Muthukumar… - Advances in Neural …, 2024 - proceedings.neurips.cc
Empirical risk minimization (ERM) of neural networks is prone to over-reliance on spurious correlations and poor generalization on minority groups. The recent deep feature …
D Teney, Y Lin, SJ Oh… - Advances in Neural …, 2024 - proceedings.neurips.cc
Several studies have compared the in-distribution (ID) and out-of-distribution (OOD) performance of models in computer vision and NLP. They report a frequent positive …
A major challenge to out-of-distribution generalization is reliance on spurious features— patterns that are predictive of the class label in the training data distribution, but not causally …