LGCLCVSep 28, 2021

When in Doubt: Improving Classification Performance with Alternating Normalization

arXiv:2109.13449v1663 citations
Originality Synthesis-oriented
AI Analysis

This is an incremental improvement for classification tasks, offering a general post-processing method to enhance probabilistic classifiers.

The paper tackles the problem of improving classification accuracy for challenging examples by introducing Classification with Alternating Normalization (CAN), a non-parametric post-processing step that re-adjusts predicted probabilities using high-confidence validation examples, resulting in demonstrated effectiveness across diverse tasks.

We introduce Classification with Alternating Normalization (CAN), a non-parametric post-processing step for classification. CAN improves classification accuracy for challenging examples by re-adjusting their predicted class probability distribution using the predicted class distributions of high-confidence validation examples. CAN is easily applicable to any probabilistic classifier, with minimal computation overhead. We analyze the properties of CAN using simulated experiments, and empirically demonstrate its effectiveness across a diverse set of classification tasks.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes