2020
DOI: 10.1016/j.patcog.2020.107527
|View full text |Cite
|
Sign up to set email alerts
|

Counter-examples generation from a positive unlabeled image dataset

Abstract: This paper considers the problem of positive unlabeled (PU) learning. In this context, we propose a two-stage GAN-based model. More specifically, the main contribution is to incorporate a biased PU risk within the standard GAN discriminator loss function. In this manner, the discriminator is constrained to steer the generator to converge towards the unlabeled samples distribution while diverging from the positive samples distribution. Consequently, the proposed model, referred to as D-GAN, exclusively learns t… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1

Citation Types

0
2
0

Year Published

2021
2021
2025
2025

Publication Types

Select...
5
1

Relationship

0
6

Authors

Journals

citations
Cited by 14 publications
(2 citation statements)
references
References 22 publications
0
2
0
Order By: Relevance
“…Table 1 shows the results of our S2M sampling and the baselines for the non-overlapping classes. The performance of GenPU is reported only for MNIST-3/5 due to its mode collapse issue [39,40]. In the results, our S2M sampling adopted to unconditional GAN shows promising results in terms of both accuracy and FID † .…”
Section: Sampling For Classes With Inclusionmentioning
confidence: 99%
“…Table 1 shows the results of our S2M sampling and the baselines for the non-overlapping classes. The performance of GenPU is reported only for MNIST-3/5 due to its mode collapse issue [39,40]. In the results, our S2M sampling adopted to unconditional GAN shows promising results in terms of both accuracy and FID † .…”
Section: Sampling For Classes With Inclusionmentioning
confidence: 99%
“…The PU learning method with unique abilities has achieved great success in many fields 20 . For example, to overcome the issue of sensitivity to prior knowledge, Chiaroni et al 21 put forward a two‐stage GAN‐based PU learning method. Chen et al 22 proposed a cost‐effective multilabel active learning model which combined example‐label pair selection strategy and the most reliable positive sub‐example‐label pairs.…”
Section: Related Workmentioning
confidence: 99%