Learning to Cascade: Confidence Calibration for Improving the Accuracy and Computational Cost of Cascade Inference Systems

• URL: http://arxiv.org/abs/2104.09286v1
• Date: Thu, 15 Apr 2021 07:09:09 GMT
• Title: Learning to Cascade: Confidence Calibration for Improving the Accuracy and Computational Cost of Cascade Inference Systems
• Authors: Shohei Enomoto, Takeharu Eda
• Abstract summary: 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.
• Score: 2.28438857884398
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recently, deep neural networks have become to be used in a variety of applications. While the accuracy of deep neural networks is increasing, the confidence score, which indicates the reliability of the prediction results, is becoming more important. Deep neural networks are seen as highly accurate but known to be overconfident, making it important to calibrate the confidence score. Many studies have been conducted on confidence calibration. They calibrate the confidence score of the model to match its accuracy, but it is not clear whether these confidence scores can improve the performance of systems that use confidence scores. This paper focuses on cascade inference systems, one kind of systems using confidence scores, and discusses the desired confidence score to improve system performance in terms of inference accuracy and computational cost. Based on the discussion, we propose a new confidence calibration method, Learning to Cascade. Learning to Cascade is a simple but novel method that optimizes the loss term for confidence calibration simultaneously with the original loss term. Experiments are conducted using two datasets, CIFAR-100 and ImageNet, in two system settings, and show that naive application of existing calibration methods to cascade inference systems sometimes performs worse. However, Learning to Cascade always achieves a better trade-off between inference accuracy and computational cost. The simplicity of Learning to Cascade allows it to be easily applied to improve the performance of existing systems.

Related papers

• Revisiting Confidence Estimation: Towards Reliable Failure Prediction [53.79160907725975]
  We find a general, widely existing but actually-neglected phenomenon that most confidence estimation methods are harmful for detecting misclassification errors. We propose to enlarge the confidence gap by finding flat minima, which yields state-of-the-art failure prediction performance.
  arXiv  Detail & Related papers  (2024-03-05T11:44:14Z)
• Towards Calibrated Deep Clustering Network [60.71776081164377]
  In deep clustering, the estimated confidence for a sample belonging to a particular cluster greatly exceeds its actual prediction accuracy. We propose a novel dual-head (calibration head and clustering head) deep clustering model that can effectively calibrate the estimated confidence and the actual accuracy. Extensive experiments demonstrate the proposed calibrated deep clustering model not only surpasses state-of-the-art deep clustering methods by 10 times in terms of expected calibration error but also significantly outperforms them in terms of clustering accuracy.
  arXiv  Detail & Related papers  (2024-03-04T11:23:40Z)
• Two Sides of Miscalibration: Identifying Over and Under-Confidence Prediction for Network Calibration [1.192436948211501]
  Proper confidence calibration of deep neural networks is essential for reliable predictions in safety-critical tasks. Miscalibration can lead to model over-confidence and/or under-confidence. We introduce a novel metric, a miscalibration score, to identify the overall and class-wise calibration status. We use the class-wise miscalibration score as a proxy to design a calibration technique that can tackle both over and under-confidence.
  arXiv  Detail & Related papers  (2023-08-06T17:59:14Z)
• Dual Focal Loss for Calibration [21.663687352629225]
  We propose a new loss function by focusing on dual logits. By maximizing the gap between these two logits, our proposed dual focal loss can achieve a better balance between over-confidence and under-confidence.
  arXiv  Detail & Related papers  (2023-05-23T04:19:16Z)
• Can pruning improve certified robustness of neural networks? [106.03070538582222]
  We show that neural network pruning can improve empirical robustness of deep neural networks (NNs) Our experiments show that by appropriately pruning an NN, its certified accuracy can be boosted up to 8.2% under standard training. We additionally observe the existence of certified lottery tickets that can match both standard and certified robust accuracies of the original dense models.
  arXiv  Detail & Related papers  (2022-06-15T05:48:51Z)
• An Underexplored Dilemma between Confidence and Calibration in Quantized Neural Networks [0.0]
  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.
  arXiv  Detail & Related papers  (2021-11-10T14:37:16Z)
• Uncertainty-sensitive Activity Recognition: a Reliability Benchmark and the CARING Models [37.60817779613977]
  We present the first study of how welthe confidence values of modern action recognition architectures indeed reflect the probability of the correct outcome. We introduce a new approach which learns to transform the model output into realistic confidence estimates through an additional calibration network.
  arXiv  Detail & Related papers  (2021-01-02T15:41:21Z)
• Uncertainty-Aware Deep Calibrated Salient Object Detection [74.58153220370527]
  Existing deep neural network based salient object detection (SOD) methods mainly focus on pursuing high network accuracy. These methods overlook the gap between network accuracy and prediction confidence, known as the confidence uncalibration problem. We introduce an uncertaintyaware deep SOD network, and propose two strategies to prevent deep SOD networks from being overconfident.
  arXiv  Detail & Related papers  (2020-12-10T23:28:36Z)
• Confidence-Aware Learning for Deep Neural Networks [4.9812879456945]
  We propose a method of training deep neural networks with a novel loss function, named Correctness Ranking Loss. It regularizes class probabilities explicitly to be better confidence estimates in terms of ordinal ranking according to confidence. It has almost the same computational costs for training as conventional deep classifiers and outputs reliable predictions by a single inference.
  arXiv  Detail & Related papers  (2020-07-03T02:00:35Z)
• 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)
• Binary Classification from Positive Data with Skewed Confidence [85.18941440826309]
  Positive-confidence (Pconf) classification is a promising weakly-supervised learning method. In practice, the confidence may be skewed by bias arising in an annotation process. We introduce the parameterized model of the skewed confidence, and propose the method for selecting the hyper parameter.
  arXiv  Detail & Related papers  (2020-01-29T00:04:36Z)

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.