• Corpus ID: 239049751

Evaluation of Various Open-Set Medical Imaging Tasks with Deep Neural Networks

  title={Evaluation of Various Open-Set Medical Imaging Tasks with Deep Neural Networks},
  author={Zongyuan Ge and Xin Wang},
  • Z. Ge, Xin Wang
  • Published 21 October 2021
  • Computer Science, Engineering
  • ArXiv
The current generation of deep neural networks has achieved close-to-human results on “closed-set” image recognition; that is, the classes being evaluated overlap with the training classes. Many recent methods attempt to address the importance of the unknown, which are termed “open-set” recognition algorithms, try to reject unknown classes as well as maintain high recognition accuracy on known classes. However, it is still unclear how different general domain-trained openset methods from… 

Figures and Tables from this paper


Progressive Transfer Learning and Adversarial Domain Adaptation for Cross-Domain Skin Disease Classification
This paper presents two methods for a novel task of cross-domain skin disease recognition and proposes to adopt adversarial learning as a domain adaptation technique to perform invariant attribute translation from source to target domain in order to improve the recognition performance.
Towards Open Set Deep Networks
  • Abhijit Bendale, T. Boult
  • Computer Science
    2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2016
The proposed OpenMax model significantly outperforms open set recognition accuracy of basic deep networks as well as deep networks with thresholding of SoftMax probabilities, and it is proved that the OpenMax concept provides bounded open space risk, thereby formally providing anopen set recognition solution.
Recent Advances in Open Set Recognition: A Survey
This paper provides a comprehensive survey of existing open set recognition techniques covering various aspects ranging from related definitions, representations of models, datasets, evaluation criteria, and algorithm comparisons to highlight the limitations of existing approaches and point out some promising subsequent research directions.
A survey on deep learning in medical image analysis
This paper reviews the major deep learning concepts pertinent to medical image analysis and summarizes over 300 contributions to the field, most of which appeared in the last year, to survey the use of deep learning for image classification, object detection, segmentation, registration, and other tasks.
Generative OpenMax for Multi-Class Open Set Classification
The proposed method, called G-OpenMax, extends OpenMax by employing generative adversarial networks (GANs) for novel category image synthesis and provides a way to visualize samples representing the unknown classes from open space.
U-Net: Convolutional Networks for Biomedical Image Segmentation
It is shown that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.
Open Set Domain Adaptation
This work learns a mapping from the source to the target domain by jointly solving an assignment problem that labels those target instances that potentially belong to the categories of interest present in the source dataset.
C2AE: Class Conditioned Auto-Encoder for Open-Set Recognition
An open-set recognition algorithm using class conditioned auto-encoders with novel training and testing methodologies is proposed and experiments show that the proposed method performs significantly better than the state of the art methods.
Toward Open Set Recognition
This paper explores the nature of open set recognition and formalizes its definition as a constrained minimization problem, and introduces a novel “1-vs-set machine,” which sculpts a decision space from the marginal distances of a 1-class or binary SVM with a linear kernel.
Dermatologist-level classification of skin cancer with deep neural networks
This work demonstrates an artificial intelligence capable of classifying skin cancer with a level of competence comparable to dermatologists, trained end-to-end from images directly, using only pixels and disease labels as inputs.