Corpus ID: 211572619

DROCC: Deep Robust One-Class Classification

@article{Goyal2020DROCCDR,
  title={DROCC: Deep Robust One-Class Classification},
  author={Sachin Goyal and Aditi Raghunathan and Moksh Jain and H. Simhadri and Prateek Jain},
  journal={ArXiv},
  year={2020},
  volume={abs/2002.12718}
}
Classical approaches for one-class problems such as one-class SVM and isolation forest require careful feature engineering when applied to structured domains like images. State-of-the-art methods aim to leverage deep learning to learn appropriate features via two main approaches. The first approach based on predicting transformations (Golan & El-Yaniv, 2018; Hendrycks et al., 2019a) while successful in some domains, crucially depends on an appropriate domain-specific set of transformations that… Expand
12 Citations
Multi-view Deep One-class Classification: A Systematic Exploration
  • Siqi Wang, Jiyuan Liu, +5 authors Jianping Yin
  • Computer Science
  • ArXiv
  • 2021
  • PDF
A Hierarchical Transformation-Discriminating Generative Model for Few Shot Anomaly Detection
  • Highly Influenced
  • PDF
A Unifying Review of Deep and Shallow Anomaly Detection
  • 17
  • PDF
Neural Transformation Learning for Deep Anomaly Detection Beyond Images
  • Highly Influenced
  • PDF
Self-Taught Semi-Supervised Anomaly Detection on Upper Limb X-rays
  • Highly Influenced
  • PDF
Unsupervised Learning of Multi-level Structures for Anomaly Detection
  • Songmin Dai, Jide Li, Lu Wang, Congcong Zhu, Yifan Wu, Xiaoqiang Li
  • Computer Science
  • ArXiv
  • 2021
  • PDF
An Experimental Study of Semantic Continuity for Deep Learning Models
  • PDF
An End-to-End Context Aware Anomaly Detection System
...
1
2
...

References

SHOWING 1-10 OF 46 REFERENCES
Deep One-Class Classification
  • 335
  • Highly Influential
  • PDF
Anomaly Detection With Multiple-Hypotheses Predictions
  • 16
  • PDF
Deep Anomaly Detection Using Geometric Transformations
  • 144
  • PDF
Learning Multiple Layers of Features from Tiny Images
  • 11,389
  • Highly Influential
  • PDF
Deep Autoencoding Gaussian Mixture Model for Unsupervised Anomaly Detection
  • 345
  • PDF
Deep Semi-Supervised Anomaly Detection
  • 72
  • Highly Influential
  • PDF
Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty
  • 177
  • Highly Influential
  • PDF
Deep Clustering for Unsupervised Learning of Visual Features
  • 687
  • PDF
Unsupervised Learning of Video Representations using LSTMs
  • 1,640
  • PDF
MobileNetV2: Inverted Residuals and Linear Bottlenecks
  • 4,065
  • Highly Influential
  • PDF
...
1
2
3
4
5
...