2020

Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Data

Hsu, Yen-Chang, Shen, Yilin, Jin, Hongxia et al.

Understand

Deep neural networks have attained remarkable performance when applied to data that comes from the same distribution as that of the training set, but can significantly degrade otherwise.

Therefore, detecting whether an example is out-of-distribution (OoD) is crucial to enable a system that can reject such samples or alert users.
Recent works have made significant progress on OoD benchmarks consisting of small image datasets.
However, many recent methods based on neural networks rely on training or tuning with both in-distribution and out-of-distribution data.

Built on

The nearest neighbor classification rule with a reject option
Martin E Hellman · 1970
Earlier work this paper cites.
Adacos: Adaptively scaling cosine logits for effectively learning deep face representations
Xiao Zhang, Rui Zhao, Yu Qiao, Xiaogang Wang, and Hongsheng Li · 2002
Earlier work this paper cites.
Learning multiple layers of features from tiny images
Alex Krizhevsky et al · 2009
Earlier work this paper cites.
Reading digits in natural images with unsupervised feature learning
Yuval Netzer, Tao Wang, Adam Coates, Alessandro Bissacco, Bo Wu, and Andrew Y. Ng · 2011
Earlier work this paper cites.
Intriguing properties of neural networks
Original
Christian Szegedy, Wojciech Zaremba, Ilya Sutskever, Joan Bruna, Dumitru Erhan, Ian Goodfellow, and Rob Fergus · 2013
Earlier work this paper cites.
Towards open world recognition
Abhijit Bendale and Terrance Boult · 2015
Earlier work this paper cites.
Delving deep into rectifiers: Surpassing human-level performance on imagenet classification
Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun · 2015
Earlier work this paper cites.
Distilling the knowledge in a neural network
Original
Geoffrey Hinton, Oriol Vinyals, and Jeff Dean · 2015
Earlier work this paper cites.
Deep neural networks are easily fooled: High confidence predictions for unrecognizable images
Anh Nguyen, Jason Yosinski, and Jeff Clune · 2015
Earlier work this paper cites.
Visual domain adaptation: A survey of recent advances
Vishal M Patel, Raghuraman Gopalan, Ruonan Li, and Rama Chellappa · 2015
Earlier work this paper cites.
Transfer representation-learning for anomaly detection
J Andrews, Thomas Tanay, Edward J Morton, and Lewis D Griffin · 2016
Earlier work this paper cites.
Towards open set deep networks
Abhijit Bendale and Terrance E Boult · 2016
Earlier work this paper cites.
Learning with rejection
Corinna Cortes, Giulia DeSalvo, and Mehryar Mohri · 2016
Earlier work this paper cites.
Dropout as a bayesian approximation: Representing model uncertainty in deep learning
Yarin Gal and Zoubin Ghahramani · 2016
Earlier work this paper cites.

Similar

Identity mappings in deep residual networks
Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun · 2016
Cited alongside, same era.
Wide residual networks
Original
Sergey Zagoruyko and Nikos Komodakis · 2016
Cited alongside, same era.
Selective classification for deep neural networks
Yonatan Geifman and Ran El-Yaniv · 2017
Cited alongside, same era.
On calibration of modern neural networks
Chuan Guo, Geoff Pleiss, Yu Sun, and Kilian Q Weinberger · 2017
Cited alongside, same era.
A baseline for detecting misclassified and out-of-distribution examples in neural networks
Dan Hendrycks and Kevin Gimpel · 2017
Cited alongside, same era.
Densely connected convolutional networks
Gao Huang, Zhuang Liu, Laurens Van Der Maaten, and Kilian Q Weinberger · 2017
Cited alongside, same era.
Simple and scalable predictive uncertainty estimation using deep ensembles
Balaji Lakshminarayanan, Alexander Pritzel, and Charles Blundell · 2017
Cited alongside, same era.
Enhancing the reliability of out-of-distribution image detection in neural networks
Original
Shiyu Liang, Yixuan Li, and R Srikant · 2017
Cited alongside, same era.
Pixelcnn++: Improving the pixelcnn with discretized logistic mixture likelihood and other modifications
Tim Salimans, Andrej Karpathy, Xi Chen, and Diederik P Kingma · 2017
Cited alongside, same era.
Generative ensembles for robust anomaly detection
Original
Hyunsun Choi and Eric Jang · 2018
Cited alongside, same era.
Reducing network agnostophobia
Akshay Raj Dhamija, Manuel Günther, and Terrance Boult · 2018
Cited alongside, same era.
Training confidence-calibrated classifiers for detecting out-of-distribution samples
Kimin Lee, Honglak Lee, Kibok Lee, and Jinwoo Shin · 2018
Cited alongside, same era.

Then

Predictive uncertainty estimation via prior networks
Andrey Malinin and Mark Gales · 2018
Later among the works it cites.
Metric learning for novelty and anomaly detection
Original
Marc Masana, Idoia Ruiz, Joan Serrat, Joost van de Weijer, and Antonio M Lopez · 2018
Later among the works it cites.
Do deep generative models know what they don’t know?
Original
Eric Nalisnick, Akihiro Matsukawa, Yee Whye Teh, Dilan Gorur, and Balaji Lakshminarayanan · 2018
Later among the works it cites.
Relaxed softmax: Efficient confidence auto-calibration for safe pedestrian detection
Lukas Neumann, Andrew Zisserman, and Andrea Vedaldi · 2018
Later among the works it cites.
Moment matching for multi-source domain adaptation
Original
Xingchao Peng, Qinxun Bai, Xide Xia, Zijun Huang, Kate Saenko, and Bo Wang · 2018
Later among the works it cites.
Out-of-distribution detection using multiple semantic label representations
Gabi Shalev, Yossi Adi, and Joseph Keshet · 2018
Later among the works it cites.
Out-of-distribution detection using an ensemble of self supervised leave-out classifiers
Apoorv Vyas, Nataraj Jammalamadaka, Xia Zhu, Dipankar Das, Bharat Kaul, and Theodore L Willke · 2018
Later among the works it cites.
Deep anomaly detection with outlier exposure
Dan Hendrycks, Mantas Mazeika, and Thomas G Dietterich · 2019
Later among the works it cites.
Reverse kl-divergence training of prior networks: Improved uncertainty and adversarial robustness
Andrey Malinin and Mark Gales · 2019
Later among the works it cites.
Ensemble distribution distillation
Andrey Malinin, Bruno Mlodozeniec, and Mark Gales · 2019
Later among the works it cites.
Likelihood ratios for out-of-distribution detection
Original
Jie Ren, Peter J Liu, Emily Fertig, Jasper Snoek, Ryan Poplin, Mark A DePristo, Joshua V Dillon, and Balaji Lakshminarayanan · 2019
Later among the works it cites.
A less biased evaluation of ood sample detectors
Alireza Shafaei, Mark Schmidt, and James Little · 2019
Later among the works it cites.
Hyperparameter-free out-of-distribution detection using softmax of scaled cosine similarity
Engkarat Techapanurak and Takayuki Okatani · 2019
Later among the works it cites.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…