When in Doubt: Improving Classification Performance with Alternating Normalization
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 (1)
Tasks
ClassificationSimilar Papers 제목 키워드 기반
TubeDAgger: Reducing the Number of Expert Interventions with Stochastic Reach-Tubes
Interactive Imitation Learning deals with training a novice policy from expert demonstrations in an online fashion. The established DAgger algorithm trains a robust novice policy by alternating between interacting with t…
Normalization Layers Are All That Sharpness-Aware Minimization Needs
Sharpness-aware minimization (SAM) was proposed to reduce sharpness of minima and has been shown to enhance generalization performance in various settings. In this work we show that perturbing only the affine normalizati…
AllHow Important is Weight Symmetry in Backpropagation?
Gradient backpropagation (BP) requires symmetric feedforward and feedback connections -- the same weights must be used for forward and backward passes. This "weight transport problem" (Grossberg 1987) is thought to be on…
Handwritten Digit RecognitionImage ClassificationIs normalization indispensable for training deep neural network?
Normalization operations are widely used to train deep neural networks, and they can improve both convergence and generalization in most tasks. The theories for normalization's effectiveness and new forms of normalizatio…
General Classificationimage-classificationImage ClassificationMachine Translation+4Measuring Classification Decision Certainty and Doubt
Quantitative characterizations and estimations of uncertainty are of fundamental importance in optimization and decision-making processes. Herein, we propose intuitive scores, which we call certainty and doubt, that can …
ClassificationDecision Making