eGAN: Unsupervised Approach to Class Imbalance Using Transfer Learning
نویسندگان
چکیده
Class imbalance is an inherent problem in many machine learning classification tasks. This often leads to learned models that are unusable for any practical purpose. In this study, we explore unsupervised approach address class by leveraging transfer from pre-trained image models. To end, encoder-based Generative Adversarial Network (eGAN) proposed which modifies the generator of a GAN introducing encoder module and adopts loss function directly classify majority minority class. best our knowledge, first work tackle using GAN-based rather than augmenting dataset with synthesized fake images. Our eliminates epistemic uncertainty model predictions, as \(P(minority)\) \(P(majority)\) need not sum up 1. The impact combinations different at discriminator level also explored. Best result 0.69 F1-score was obtained on CIFAR-10 task enforced ratio 1:2500. implementation code available - https://github.com/demolakstate/eGAN_addressing_class_imbalance_with_transfer_learning_on_GAN.git.
منابع مشابه
Class Imbalance Learning
This report presents the work completed since the thesis proposal and the revised plan for the future PhD study. Two main issues have been discussed so far: diversity analysis of ensemble models in class imbalance learning, exploration of negative correlation learning on imbalanced data. Experimental design and main conclusions are simply described. More details are included in the two papers i...
متن کاملUnsupervised and Transfer Learning Challenge: a Deep Learning Approach
Learning good representations from a large set of unlabeled data is a particularly challenging task. Recent work (see Bengio (2009) for a review) shows that training deep architectures is a good way to extract such representations, by extracting and disentangling gradually higher-level factors of variation characterizing the input distribution. In this paper, we describe different kinds of laye...
متن کاملClass Imbalance and Active Learning
The rich history of predictive modeling has culminated in a diverse set of techniques capable of making accurate predictions on many real-world problems. Many of these techniques demand training, whereby a set of instances with ground-truth labels (values of a dependent variable) are observed by a model-building process that attempts to capture, at least in part, the relationship between the fe...
متن کاملUnsupervised and Transfer Learning
We organized a data mining challenge in “unsupervised and transfer learning” (the UTL challenge) followed by a workshop of the same name at the ICML 2011 conference in Bellevue, Washington1. This introduction presents the highlights of the outstanding contributions that were made, which are regrouped in this issue of JMLR W&CP. Novel methodologies emerged to capitalize on large volumes of unlab...
متن کاملMeta-Unsupervised-Learning: A supervised approach to unsupervised learning
We introduce a new paradigm to investigate unsupervised learning, reducing unsupervised learning to supervised learning. Specifically, we mitigate the subjectivity in unsupervised decision-making by leveraging knowledge acquired from prior, possibly heterogeneous, supervised learning tasks. We demonstrate the versatility of our framework via comprehensive expositions and detailed experiments on...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Lecture Notes in Computer Science
سال: 2021
ISSN: ['1611-3349', '0302-9743']
DOI: https://doi.org/10.1007/978-3-030-89128-2_31