Corpus ID: 232168629

Learning Invariant Representations across Domains and Tasks

@article{Wang2021LearningIR,
  title={Learning Invariant Representations across Domains and Tasks},
  author={Jindong Wang and W. Feng and C. Liu and Chaohui Yu and Min Du and Renjun Xu and Tao Qin and T. Liu},
  journal={ArXiv},
  year={2021},
  volume={abs/2103.05114}
}
Being expensive and time-consuming to collect massive COVID-19 image samples to train deep classification models, transfer learning is a promising approach by transferring knowledge from the abundant typical pneumonia datasets for COVID-19 image classification. However, negative transfer may deteriorate the performance due to the feature distribution divergence between two datasets and task semantic difference in diagnosing pneumonia and COVID-19 that rely on different characteristics. It is… Expand

References

SHOWING 1-10 OF 49 REFERENCES
A Survey on Transfer Learning
  • 10,547
  • Highly Influential
  • PDF
Towards Discriminability and Diversity: Batch Nuclear-Norm Maximization Under Label Insufficient Situations
  • 27
  • Highly Influential
  • PDF
Bridging Theory and Algorithm for Domain Adaptation
  • 112
  • Highly Influential
  • PDF
Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization
  • 2,655
  • Highly Influential
  • PDF
Deep Hashing Network for Unsupervised Domain Adaptation
  • 439
  • Highly Influential
  • PDF
Unsupervised Domain Adaptation by Backpropagation
  • 2,156
  • Highly Influential
  • PDF
COVID-19 Screening on Chest X-ray Images Using Deep Learning based Anomaly Detection
  • 190
  • PDF
Curated dataset for covid-19 posterior-anterior chest radiography images (xrays)
  • 2020
What is being transferred in transfer learning?
  • 21
  • PDF
...
1
2
3
4
5
...