An Underexplored Dilemma between Confidence and Calibration in Quantized Neural Networks

• URL: http://arxiv.org/abs/2111.08163v1
• Date: Wed, 10 Nov 2021 14:37:16 GMT
• Title: An Underexplored Dilemma between Confidence and Calibration in Quantized Neural Networks
• Authors: Guoxuan Xia, Sangwon Ha, Tiago Azevedo, Partha Maji
• Abstract summary: Modern convolutional neural networks (CNNs) are known to be overconfident in terms of their calibration on unseen input data. This is undesirable if the probabilities predicted are to be used for downstream decision making. We show that this robustness can be partially explained by the calibration behavior of modern CNNs, and may be improved with overconfidence.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Modern convolutional neural networks (CNNs) are known to be overconfident in terms of their calibration on unseen input data. That is to say, they are more confident than they are accurate. This is undesirable if the probabilities predicted are to be used for downstream decision making. When considering accuracy, CNNs are also surprisingly robust to compression techniques, such as quantization, which aim to reduce computational and memory costs. We show that this robustness can be partially explained by the calibration behavior of modern CNNs, and may be improved with overconfidence. This is due to an intuitive result: low confidence predictions are more likely to change post-quantization, whilst being less accurate. High confidence predictions will be more accurate, but more difficult to change. Thus, a minimal drop in post-quantization accuracy is incurred. This presents a potential conflict in neural network design: worse calibration from overconfidence may lead to better robustness to quantization. We perform experiments applying post-training quantization to a variety of CNNs, on the CIFAR-100 and ImageNet datasets.

Related papers

• Bridging Precision and Confidence: A Train-Time Loss for Calibrating Object Detection [58.789823426981044]
  We propose a novel auxiliary loss formulation that aims to align the class confidence of bounding boxes with the accurateness of predictions. Our results reveal that our train-time loss surpasses strong calibration baselines in reducing calibration error for both in and out-domain scenarios.
  arXiv  Detail & Related papers  (2023-03-25T08:56:21Z)
• Improving the Accuracy and Robustness of CNNs Using a Deep CCA Neural Data Regularizer [2.026424957803652]
  As convolutional neural networks (CNNs) become more accurate at object recognition, their representations become more similar to the primate visual system. Previous attempts to address this question showed very modest gains in accuracy, owing in part to limitations of the regularization method. We develop a new neural data regularizer for CNNs that uses Deep Correlation Analysis (DCCA) to optimize the resemblance of the CNN's image representations to that of the monkey visual cortex.
  arXiv  Detail & Related papers  (2022-09-06T15:40:39Z)
• Bayesian Confidence Calibration for Epistemic Uncertainty Modelling [4.358626952482686]
  We introduce a framework to obtain confidence estimates in conjunction with an uncertainty of the calibration method. We achieve state-of-the-art calibration performance for object detection calibration.
  arXiv  Detail & Related papers  (2021-09-21T10:53:16Z)
• On the Dark Side of Calibration for Modern Neural Networks [65.83956184145477]
  We show the breakdown of expected calibration error (ECE) into predicted confidence and refinement. We highlight that regularisation based calibration only focuses on naively reducing a model's confidence. We find that many calibration approaches with the likes of label smoothing, mixup etc. lower the utility of a DNN by degrading its refinement.
  arXiv  Detail & Related papers  (2021-06-17T11:04:14Z)
• Learning to Cascade: Confidence Calibration for Improving the Accuracy and Computational Cost of Cascade Inference Systems [2.28438857884398]
  Deep neural networks are highly accurate but known to be overconfident. It is not clear whether confidence scores can improve the performance of systems that use confidence scores. We propose a new confidence calibration method, Learning to Cascade.
  arXiv  Detail & Related papers  (2021-04-15T07:09:09Z)
• Improving Uncertainty Calibration via Prior Augmented Data [56.88185136509654]
  Neural networks have proven successful at learning from complex data distributions by acting as universal function approximators. They are often overconfident in their predictions, which leads to inaccurate and miscalibrated probabilistic predictions. We propose a solution by seeking out regions of feature space where the model is unjustifiably overconfident, and conditionally raising the entropy of those predictions towards that of the prior distribution of the labels.
  arXiv  Detail & Related papers  (2021-02-22T07:02:37Z)
• S2-BNN: Bridging the Gap Between Self-Supervised Real and 1-bit Neural Networks via Guided Distribution Calibration [74.5509794733707]
  We present a novel guided learning paradigm from real-valued to distill binary networks on the final prediction distribution. Our proposed method can boost the simple contrastive learning baseline by an absolute gain of 5.515% on BNNs. Our method achieves substantial improvement over the simple contrastive learning baseline, and is even comparable to many mainstream supervised BNN methods.
  arXiv  Detail & Related papers  (2021-02-17T18:59:28Z)
• On Calibration of Mixup Training for Deep Neural Networks [1.6242924916178283]
  We argue and provide empirical evidence that, due to its fundamentals, Mixup does not necessarily improve calibration. Our loss is inspired by Bayes decision theory and introduces a new training framework for designing losses for probabilistic modelling. We provide state-of-the-art accuracy with consistent improvements in calibration performance.
  arXiv  Detail & Related papers  (2020-03-22T16:54:31Z)
• Calibrating Deep Neural Networks using Focal Loss [77.92765139898906]
  Miscalibration is a mismatch between a model's confidence and its correctness. We show that focal loss allows us to learn models that are already very well calibrated. We show that our approach achieves state-of-the-art calibration without compromising on accuracy in almost all cases.
  arXiv  Detail & Related papers  (2020-02-21T17:35:50Z)
• Widening and Squeezing: Towards Accurate and Efficient QNNs [125.172220129257]
  Quantization neural networks (QNNs) are very attractive to the industry because their extremely cheap calculation and storage overhead, but their performance is still worse than that of networks with full-precision parameters. Most of existing methods aim to enhance performance of QNNs especially binary neural networks by exploiting more effective training techniques. We address this problem by projecting features in original full-precision networks to high-dimensional quantization features.
  arXiv  Detail & Related papers  (2020-02-03T04:11:13Z)

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.