Anticipate, Ensemble and Prune: Improving Convolutional Neural Networks via Aggregated Early Exits

• URL: http://arxiv.org/abs/2301.12168v1
• Date: Sat, 28 Jan 2023 11:45:11 GMT
• Title: Anticipate, Ensemble and Prune: Improving Convolutional Neural Networks via Aggregated Early Exits
• Authors: Simone Sarti, Eugenio Lomurno, Matteo Matteucci
• Abstract summary: We present Anticipate, Ensemble and Prune (AEP), a new training technique based on weighted ensembles of early exits. AEP can yield average accuracy improvements of up to 15% over traditional training.
• Score: 7.967995669387532
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Today, artificial neural networks are the state of the art for solving a variety of complex tasks, especially in image classification. Such architectures consist of a sequence of stacked layers with the aim of extracting useful information and having it processed by a classifier to make accurate predictions. However, intermediate information within such models is often left unused. In other cases, such as in edge computing contexts, these architectures are divided into multiple partitions that are made functional by including early exits, i.e. intermediate classifiers, with the goal of reducing the computational and temporal load without extremely compromising the accuracy of the classifications. In this paper, we present Anticipate, Ensemble and Prune (AEP), a new training technique based on weighted ensembles of early exits, which aims at exploiting the information in the structure of networks to maximise their performance. Through a comprehensive set of experiments, we show how the use of this approach can yield average accuracy improvements of up to 15% over traditional training. In its hybrid-weighted configuration, AEP's internal pruning operation also allows reducing the number of parameters by up to 41%, lowering the number of multiplications and additions by 18% and the latency time to make inference by 16%. By using AEP, it is also possible to learn weights that allow early exits to achieve better accuracy values than those obtained from single-output reference models.

Related papers

• YOSO: You-Only-Sample-Once via Compressed Sensing for Graph Neural Network Training [9.02251811867533]
  YOSO (You-Only-Sample-Once) is an algorithm designed to achieve efficient training while preserving prediction accuracy. YOSO not only avoids costly computations in traditional compressed sensing (CS) methods, such as orthonormal basis calculations, but also ensures high-probability accuracy retention.
  arXiv  Detail & Related papers  (2024-11-08T16:47:51Z)
• Unrolled denoising networks provably learn optimal Bayesian inference [54.79172096306631]
  We prove the first rigorous learning guarantees for neural networks based on unrolling approximate message passing (AMP) For compressed sensing, we prove that when trained on data drawn from a product prior, the layers of the network converge to the same denoisers used in Bayes AMP.
  arXiv  Detail & Related papers  (2024-09-19T17:56:16Z)
• Compound Batch Normalization for Long-tailed Image Classification [77.42829178064807]
  We propose a compound batch normalization method based on a Gaussian mixture. It can model the feature space more comprehensively and reduce the dominance of head classes. The proposed method outperforms existing methods on long-tailed image classification.
  arXiv  Detail & Related papers  (2022-12-02T07:31:39Z)
• AIO-P: Expanding Neural Performance Predictors Beyond Image Classification [22.743278613519152]
  We propose a novel All-in-One Predictor (AIO-P) to pretrain neural predictors on architecture examples. AIO-P can achieve Mean Absolute Error (MAE) and Spearman's Rank Correlation (SRCC) below 1% and above 0.5, respectively.
  arXiv  Detail & Related papers  (2022-11-30T18:30:41Z)
• Pushing the Efficiency Limit Using Structured Sparse Convolutions [82.31130122200578]
  We propose Structured Sparse Convolution (SSC), which leverages the inherent structure in images to reduce the parameters in the convolutional filter. We show that SSC is a generalization of commonly used layers (depthwise, groupwise and pointwise convolution) in efficient architectures'' Architectures based on SSC achieve state-of-the-art performance compared to baselines on CIFAR-10, CIFAR-100, Tiny-ImageNet, and ImageNet classification benchmarks.
  arXiv  Detail & Related papers  (2022-10-23T18:37:22Z)
• Layer Ensembles [95.42181254494287]
  We introduce a method for uncertainty estimation that considers a set of independent categorical distributions for each layer of the network. We show that the method can be further improved by ranking samples, resulting in models that require less memory and time to run.
  arXiv  Detail & Related papers  (2022-10-10T17:52:47Z)
• Towards Disentangling Information Paths with Coded ResNeXt [11.884259630414515]
  We take a novel approach to enhance the transparency of the function of the whole network. We propose a neural network architecture for classification, in which the information that is relevant to each class flows through specific paths.
  arXiv  Detail & Related papers  (2022-02-10T21:45:49Z)
• Analytically Tractable Inference in Deep Neural Networks [0.0]
  Tractable Approximate Inference (TAGI) algorithm was shown to be a viable and scalable alternative to backpropagation for shallow fully-connected neural networks. We are demonstrating how TAGI matches or exceeds the performance of backpropagation, for training classic deep neural network architectures.
  arXiv  Detail & Related papers  (2021-03-09T14:51:34Z)
• Rapid Structural Pruning of Neural Networks with Set-based Task-Adaptive Meta-Pruning [83.59005356327103]
  A common limitation of most existing pruning techniques is that they require pre-training of the network at least once before pruning. We propose STAMP, which task-adaptively prunes a network pretrained on a large reference dataset by generating a pruning mask on it as a function of the target dataset. We validate STAMP against recent advanced pruning methods on benchmark datasets.
  arXiv  Detail & Related papers  (2020-06-22T10:57:43Z)
• Fitting the Search Space of Weight-sharing NAS with Graph Convolutional Networks [100.14670789581811]
  We train a graph convolutional network to fit the performance of sampled sub-networks. With this strategy, we achieve a higher rank correlation coefficient in the selected set of candidates.
  arXiv  Detail & Related papers  (2020-04-17T19:12:39Z)
• Anytime Inference with Distilled Hierarchical Neural Ensembles [32.003196185519]
  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. We propose Hierarchical Neural Ensembles (HNE), a novel framework to embed an ensemble of multiple networks in a hierarchical tree structure, sharing intermediate layers. Our experiments show that, compared to previous anytime inference models, HNE provides state-of-the-art accuracy-computate trade-offs on the CIFAR-10/100 and ImageNet datasets.
  arXiv  Detail & Related papers  (2020-03-03T12:13:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.