Improved model training for few-class, few-shot tasks.
problem Meta-learning algorithms struggle in many-shot and many-class settings.
method Joint training approach combining transfer-learning and meta-learning.
result Improved generalization performance on unseen tasks.
Let G be a word hyperbolic group. We prove that the algebraic K-theory groups of $\dbZ [G]$, $K_n(\dbZ[G])$, have finite rank for all $n\in \dbZ$. For a few classes of groups, we give explicit formulas for the ranks of the algebraic K-theory groups of their group rings.
The abstract explores analogues of Hodge theory in Lie algebroids.
problem Exploring analogues of Hodge theory in Lie algebroids.
method Establishing equivalence of conditions and applying algebraic theory to geometric setting.
result Equivalence of analogues of Hodge theory conditions in Lie algebroids.
We consider the bulk algebra and topological D-brane category arising from the differential model of the open-closed B-type topological Landau-Ginzburg theory defined by a pair (X,W), where X is a non-compact Calabi-Yau manifold and W has compact critical set. When X is a Stein manifold (but not restricted to b…
New concept of partial law invariance connects decision theory and financial risk management.
problem Connecting decision theory and financial risk management under uncertainty.
method Characterizing partially law-invariant coherent risk measures via a novel representation formula.
result Strong partial law invariance bridges the gap between existing risk measure representations.
Study feasibility of deep neural networks for Euro banknote classification.
problem Meeting special requirements for banknote classification by central banks.
method Training and testing deep neural networks on state-of-the-art GPU hardware for few classes and 0-class rejection.
result Deep neural networks can meet central bank requirements for banknote classification.
Distill-Net creates efficient CNNs for IoT by distilling complex models.
problem Efficient inference of deep CNNs on resource-constrained IoT platforms.
method Application-specific distillation of deep CNNs.
result Efficient inference on resource-constrained platforms with high accuracy.
Generative replay improves continual learning by using generated data as negative examples.
problem Catastrophic forgetting in continual learning.
method Using generative models to provide negative examples for new classes.
result Generative replay can improve learning new classes even when existing approaches fail.
Paper proposes SAN and SN for zero-shot sketch-based image retrieval.
problem Handling unseen classes in sketch-based image retrieval.
method Generative approach using Stacked Adversarial Network (SAN) and Siamese Network (SN).
result Significant improvement in standard and generalized ZSL settings.
Tutorial on estimating PD using survival analysis under IFRS 9.
problem Dynamic estimation of credit losses under IFRS 9.
method Discrete-time survival analysis for estimating PD.
result Development of a comprehensive tutorial and diagnostic measures.
Layer normalization improves federated learning with skewed labels.
problem Label skewness in federated learning datasets.
method Identified feature normalization as key mechanism; applied to latent features before classifier.
result Normalization accelerates global training and improves convergence under extreme label shift.
ELF improves long-tailed classification by focusing on hard examples.
problem Overfitting to majority classes in long-tailed data distributions.
method EARLY-exiting Framework with auxiliary branches.
result Improves accuracy by more than 3 percent on ImageNet LT and iNaturalist'18.
Factor graphs are important models for succinctly representing probability distributions in machine learning, coding theory, and statistical physics. Several computational problems, such as computing marginals and partition functions, arise naturally when working with factor graphs. Belief propagation is a widely deplo…
Paper tackles many-class few-shot learning with class hierarchy, improving accuracy.
problem Many-class few-shot learning problem in practical applications.
method Leverages class hierarchy to train a coarse-to-fine classifier using memory-augmented hierarchical-classification network (MahiNet).
result MahiNet outperforms state-of-the-art models on MCFS problems in both supervised and meta-learning settings.