paper-with-me

Papers

When in Doubt: Improving Classification Performance with Alternating Normalization

2021-09-28 · Findings (EMNLP) 2021 11 · Menglin Jia, Austin Reiter, Ser-Nam Lim, Yoav Artzi, Claire Cardie

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.

📄 PDF Abstract BibTeX arXiv:2109.13449

Code (1)

KMnP/can 공식 구현 pytorch

Tasks

Classification

Similar Papers 제목 키워드 기반

TubeDAgger: Reducing the Number of Expert Interventions with Stochastic Reach-Tubes

2025-10-01 · Julian Lemmel, Manuel Kranzl, Adam Lamine, Philipp Neubauer 외 arxiv

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

2023-06-07 · NeurIPS 2023 11 · Maximilian Mueller, Tiffany Vlaar, David Rolnick, Matthias Hein

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…

All

How Important is Weight Symmetry in Backpropagation?

2015-10-17 · Qianli Liao, Joel Z. Leibo, Tomaso Poggio

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 Classification

Is normalization indispensable for training deep neural network?

2020-12-01 · NeurIPS 2020 12 · Jie Shao, Kai Hu, Changhu Wang, xiangyang xue 외

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+4

Measuring Classification Decision Certainty and Doubt

2023-03-25 · Alexander M. Berenbeim, Iain J. Cruickshank, Susmit Jha, Robert H. Thomson 외

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