Cost-Sensitive Deep Learning with Layer-Wise Cost Estimation

  title={Cost-Sensitive Deep Learning with Layer-Wise Cost Estimation},
  author={Yu-An Chung and Hsuan-Tien Lin},
  journal={2020 International Conference on Technologies and Applications of Artificial Intelligence (TAAI)},
  • Yu-An Chung, Hsuan-Tien Lin
  • Published 2020
  • Computer Science
  • 2020 International Conference on Technologies and Applications of Artificial Intelligence (TAAI)
While deep neural networks have succeeded in several applications, such as image classification, object detection, and speech recognition, by reaching very high classification accuracies, it is important to note that many real-world applications demand varying costs for different types of misclassification errors, thus requiring cost-sensitive classification algorithms. Current models of deep neural networks for cost-sensitive classification are restricted to some specific network structures… Expand
Automated Detection of Sewer Pipe Defects Based on Cost-Sensitive Convolutional Neural Network
The authors propose a new auxiliary loss function Cost-Mean Loss, which allows the model to obtain the original parameters of the network to maximize the accuracy and improve the performance of the model by minimizing total misclassification costs in the learning process. Expand


Cost-Aware Pre-Training for Multiclass Cost-Sensitive Deep Learning
A novel cost-aware algorithm is proposed that takes into account the cost information into not only the training stage but also the pre-training stage of deep learning, which allows deep learning to conduct automatic feature extraction with the cost Information effectively. Expand
Deeply-Supervised Nets
The proposed deeply-supervised nets (DSN) method simultaneously minimizes classification error while making the learning process of hidden layers direct and transparent, and extends techniques from stochastic gradient methods to analyze the algorithm. Expand
Deep Residual Learning for Image Recognition
This work presents a residual learning framework to ease the training of networks that are substantially deeper than those used previously, and provides comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. Expand
Scalable Object Detection Using Deep Neural Networks
This work proposes a saliency-inspired neural network model for detection, which predicts a set of class-agnostic bounding boxes along with a single score for each box, corresponding to its likelihood of containing any object of interest. Expand
ImageNet classification with deep convolutional neural networks
A large, deep convolutional neural network was trained to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes and employed a recently developed regularization method called "dropout" that proved to be very effective. Expand
Improving object detection with deep convolutional networks via Bayesian optimization and structured prediction
This work addresses the localization problem by using a search algorithm based on Bayesian optimization that sequentially proposes candidate regions for an object bounding box, and training the CNN with a structured loss that explicitly penalizes the localization inaccuracy. Expand
Deep Neural Networks for Object Detection
This paper presents a simple and yet powerful formulation of object detection as a regression problem to object bounding box masks, and defines a multi-scale inference procedure which is able to produce high-resolution object detections at a low cost by a few network applications. Expand
Training Cost-Sensitive Neural Networks with Methods Addressing the Class Imbalance Problem
The empirical study suggests that some methods that have been believed to be effective in addressing the class imbalance problem may, in fact, only be effective on learning with imbalanced two-class data sets. Expand
Cost-sensitive dictionary learning for face recognition
A cost-sensitive dictionary learning algorithm for SRC is proposed, by which the designed dictionary is able to produce cost- sensitive sparse coding, resulting in improved classification performance in such scenarios. Expand
Very Deep Convolutional Networks for Large-Scale Image Recognition
This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers. Expand