4 papers
Environment-Conditioned Tail Reweighting for Invariant Learning under Mixed Shifts
Yuanchao Wang, Zhao-Rong Lai, Tianqi Zhong +1
Out-of-distribution generalization becomes challenging when spurious correlations vary across environments while difficult or underrepresented samples remain insufficiently emphasi…
BootOOD: Self-Supervised Out-of-Distribution Detection via Synthetic Sample Exposure under Neural Collapse
Yuanchao Wang, Tian Qin, Eduardo Valle +1
Out-of-distribution (OOD) detection is critical for deploying image classifiers in safety-sensitive environments, yet existing detectors often struggle when OOD samples are semanti…
Out-of-distribution Generalization for Total Variation based Invariant Risk Minimization
Yuanchao Wang, Zhao-Rong Lai, Tianqi Zhong
Invariant risk minimization is an important general machine learning framework that has recently been interpreted as a total variation model (IRM-TV). However, how to improve out-o…
Explaining the Attention Mechanism of End-to-End Speech Recognition Using Decision Trees
Yuanchao Wang, Wenji Du, Chenghao Cai +1
The attention mechanism has largely improved the performance of end-to-end speech recognition systems. However, the underlying behaviours of attention is not yet clearer. In this s…