paper-with-me

홈 › Papers

Fast and Accurate Inference with Adaptive Ensemble Prediction for Deep Networks

2018-01-01 · ICLR 2018 1 · Hiroshi Inoue

Ensembling multiple predictions is a widely-used technique to improve the accuracy of various machine learning tasks. In image classification tasks, for example, averaging the predictions for multiple patches extracted from the input image significantly improves accuracy. Using multiple networks trained independently to make predictions improves accuracy further. One obvious drawback of the ensembling technique is its higher execution cost during inference.% If we average 100 local predictions, the execution cost will be 100 times as high as the cost without the ensemble. This higher cost limits the real-world use of ensembling. In this paper, we first describe our insights on relationship between the probability of the prediction and the effect of ensembling with current deep neural networks; ensembling does not help mispredictions for inputs predicted with a high probability, i.e. the output from the softmax. This finding motivates us to develop a new technique called adaptive ensemble prediction, which achieves the benefits of ensembling with much smaller additional execution costs. Hence, we calculate the confidence level of the prediction for each input from the probabilities of the local predictions during the ensembling computation. If the prediction for an input reaches a high enough probability on the basis of the confidence level, we stop ensembling for this input to avoid wasting computation power. We evaluated the adaptive ensembling by using various datasets and showed that it reduces the computation cost significantly while achieving similar accuracy to the naive ensembling. We also showed that our statistically rigorous confidence-level-based termination condition reduces the burden of the task-dependent parameter tuning compared to the naive termination based on the pre-defined threshold in addition to yielding a better accuracy with the same cost.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

image-classificationImage Classification

Similar Papers 제목 키워드 기반

Conformalized Quantum DeepONet Ensembles for Scalable Operator Learning with Distribution-Free Uncertainty

2026-05-01 · Purav Matlia, Christian Moya, Guang Lin arxiv

Operator learning enables fast surrogate modeling of high-dimensional dynamical systems, but existing approaches face two fundamental limitations: quadratic inference complexity and unreliable uncertainty quantification …

Quantum Machine Learning

Anytime Inference with Distilled Hierarchical Neural Ensembles

2020-03-03 · Adria Ruiz, Jakob Verbeek

Inference in deep neural networks can be computationally expensive, and networks capable of anytime inference are important in mscenarios where the amount of compute or quantity of input data varies over time. In such ne…

DiversityImage Classification

Ensemble Distillation for Structured Prediction: Calibrated, Accurate, Fast-Choose Three

2020-10-13 · EMNLP 2020 11 · Steven Reich, David Mueller, Nicholas Andrews

Modern neural networks do not always produce well-calibrated predictions, even when trained with a proper scoring function such as cross-entropy. In classification settings, simple methods such as isotonic regression or …

Machine Translationnamed-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)+2

Faster, Lighter, More Accurate: A Deep Learning Ensemble for Content Moderation

2023-09-10 · Mohammad Hosseini, Mahmudul Hasan

To address the increasing need for efficient and accurate content moderation, we propose an efficient and lightweight deep classification ensemble structure. Our approach is based on a combination of simple visual featur…

Deep LearningPhilosophy

FourCastNet: Accelerating Global High-Resolution Weather Forecasting using Adaptive Fourier Neural Operators

2022-08-08 · Thorsten Kurth, Shashank Subramanian, Peter Harrington, Jaideep Pathak 외

Extreme weather amplified by climate change is causing increasingly devastating impacts across the globe. The current use of physics-based numerical weather prediction (NWP) limits accuracy due to high computational cost…

Weather Forecasting