Country
Test-TimeClassifierAdjustmentModulefor Model-AgnosticDomainGeneralization
Unlike existing methods that focus ontraining phase, our method focusestest phase, i.e., correcting its prediction by itself during test time.
Functional Indirection Neural Estimator for Better Out-of-distribution Generalization
Kha Pham1 Hung Le1 Man Ngo2 Truyen Tran1, 1 Applied Artificial Intelligence Institute, Deakin University, 2 Faculty of Mathematics and Computer Science, VNUHCM-University of Science, , 1 {phti, thai.le, truyen.tran}@deakin.edu.au, 2 nmman@hcmus.edu.vn
The mixing coefficients are indirectly computed through querying a separate corresponding semantic memory using the data pair. We demonstrate empirically thatFINEcanstrongly improveout-of-distribution generalization on IQ tasks that involve geometric transformations.
MinimaxLowerBoundsforTransferLearningwith LinearandOne-hiddenLayerNeuralNetworks
Despiterecentempirical success of transfer learning approaches, the benefits and fundamental limits of transfer learning are poorly understood.
MinimaxLowerBoundsforTransferLearningwith LinearandOne-hiddenLayerNeuralNetworks
Despiterecentempirical success of transfer learning approaches, the benefits and fundamental limits of transfer learning are poorly understood.
Understanding Instance-based Interpretability of Variational Auto-Encoders
Instance-based interpretation methods have been widely studied for supervised learning methods as they help explain how black box neural networks predict.
