paper-with-me

홈 › Papers

Out-of-Distribution Detection using BiGAN and MDL

2022-06-03 · Mojtaba Abolfazli, Mohammad Zaeri Arimani, Anders Host-Madsen, June Zhang, Andras Bratincsak

We consider the following problem: we have a large dataset of normal data available. We are now given a new, possibly quite small, set of data, and we are to decide if these are normal data, or if they are indicating a new phenomenon. This is a novelty detection or out-of-distribution detection problem. An example is in medicine, where the normal data is for people with no known disease, and the new dataset people with symptoms. Other examples could be in security. We solve this problem by training a bidirectional generative adversarial network (BiGAN) on the normal data and using a Gaussian graphical model to model the output. We then use universal source coding, or minimum description length (MDL) on the output to decide if it is a new distribution, in an implementation of Kolmogorov and Martin-L\"{o}f randomness. We apply the methodology to both MNIST data and a real-world electrocardiogram (ECG) dataset of healthy and patients with Kawasaki disease, and show better performance in terms of the ROC curve than similar methods.

📄 PDF Abstract BibTeX arXiv:2206.01851

Code (0)

등록된 구현이 없습니다.

Tasks

Generative Adversarial NetworkNovelty DetectionOut-of-Distribution Detection

Similar Papers 제목 키워드 기반

Unsupervised Detection of Spatiotemporal Anomalies in PMU Data Using Transformer-Based BiGAN

2025-09-30 · Muhammad Imran Hossain, Jignesh Solanki, Sarika Khushlani Solanki arxiv

Ensuring power grid resilience requires the timely and unsupervised detection of anomalies in synchrophasor data streams. We introduce T-BiGAN, a novel framework that integrates window-attention Transformers within a bid…

Combining GANs and AutoEncoders for Efficient Anomaly Detection

2020-11-16 · Fabio Carrara, Giuseppe Amato, Luca Brombin, Fabrizio Falchi 외

In this work, we propose CBiGAN -- a novel method for anomaly detection in images, where a consistency constraint is introduced as a regularization term in both the encoder and decoder of a BiGAN. Our model exhibits fair…

Adversarial AttackAnomaly DetectionDecoderImage Classification+1

Lung Cancer Risk Estimation with Incomplete Data: A Joint Missing Imputation Perspective

2021-07-25 · Riqiang Gao, Yucheng Tang, Kaiwen Xu, Ho Hin Lee 외

Data from multi-modality provide complementary information in clinical prediction, but missing data in clinical cohorts limits the number of subjects in multi-modal learning context. Multi-modal missing imputation is cha…

Imputation

Adventurer: Exploration with BiGAN for Deep Reinforcement Learning

2025-03-24 · Yongshuai Liu, Xin Liu

Recent developments in deep reinforcement learning have been very successful in learning complex, previously intractable problems. Sample efficiency and local optimality, however, remain significant challenges. To addres…

Atari GamesDeep Reinforcement LearningMuJoCoreinforcement-learning+1

Enhancement to Training of Bidirectional GAN : An Approach to Demystify Tax Fraud

2022-08-16 · Priya Mehta, Sandeep Kumar, Ravi Kumar, Ch. Sobhan Babu

Outlier detection is a challenging activity. Several machine learning techniques are proposed in the literature for outlier detection. In this article, we propose a new training approach for bidirectional GAN (BiGAN) to …

Outlier Detection