Attention-Aware Generative Adversarial Networks (ATA-GANs)

Kastaniotis, Dimitris; Ntinou, Ioanna; Tsourounis, Dimitrios; Economou, George; Fotopoulos, S.

doi:10.1109/ivmspw.2018.8448850

Cited by 37 publications

(29 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Later, the attention mechanism was introduced to GAN for image conversion. In [24], authors used Resnet-18 as a teacher network to train the discriminator of the GAN where the teacher taught the discriminator where to focus on the generated image. In [25], researchers proposed a model with attention GAN for image-to-image translation.…”

Section: Image-to-image Translation Using Gansmentioning

confidence: 99%

“…Figure 4 shows the structure of the discriminator, which is a patch-based discriminator introduced in [51], and we modified it by following [25]. In [24], authors used ResNet-18 [52] as a teacher network to generate attention maps to teach the discriminators where to focus. Inspired by [24], we use ResNet-18 as a teacher network in our model to train the generators where to focus.…”

Section: Architecture Of the Proposed Modelmentioning

confidence: 99%

See 1 more Smart Citation

Converting Optical Videos to Infrared Videos Using Attention GAN and Its Impact on Target Detection and Classification Performance

et al. 2021

View full text Add to dashboard Cite

To apply powerful deep-learning-based algorithms for object detection and classification in infrared videos, it is necessary to have more training data in order to build high-performance models. However, in many surveillance applications, one can have a lot more optical videos than infrared videos. This lack of IR video datasets can be mitigated if optical-to-infrared video conversion is possible. In this paper, we present a new approach for converting optical videos to infrared videos using deep learning. The basic idea is to focus on target areas using attention generative adversarial network (attention GAN), which will preserve the fidelity of target areas. The approach does not require paired images. The performance of the proposed attention GAN has been demonstrated using objective and subjective evaluations. Most importantly, the impact of attention GAN has been demonstrated in improved target detection and classification performance using real-infrared videos.

show abstract

Section: Image-to-image Translation Using Gansmentioning

confidence: 99%

Section: Architecture Of the Proposed Modelmentioning

confidence: 99%

Converting Optical Videos to Infrared Videos Using Attention GAN and Its Impact on Target Detection and Classification Performance

et al. 2021

View full text Add to dashboard Cite

show abstract

“…They used a U-net generator based on a modified framework that combines both pix2pix [40] and ACGAN [41] with a transferlearning technique to boost the segmentation performance across different cell modalities. In the field of HEp-2 cell image synthesis, Kastaniotis et al [42] proposed using a Teacher-network to guide the attention maps in the discriminator hidden layers in DCGAN [10] framework to improve the quality of the generated HEp-2 cell images. However, no evaluation measures have been applied in their study.…”

Section: Gans For Hep-2 Image Classificationmentioning

confidence: 99%

Studying the Applicability of Generative Adversarial Networks on HEp-2 Cell Image Augmentation

2021

View full text Add to dashboard Cite

The Anti-Nuclear Antibodies (ANAs) testing is the primary serological diagnosis screening test for autoimmune diseases. ANAs testing is conducted mainly by the Indirect Immunofluorescence (IIF) on Human Epithelial cell-substrate (HEp-2) protocol. However, due to its high variability, humansubjectivity, and low throughput, there is an insistent need to develop an efficient Computer-Aided Diagnosis system (CADs) to automate this protocol. Many recently proposed Convolutional Neural Networks (CNNs) demonstrated promising results in HEp-2 cell image classification, which is the main task of the HE-p2 IIF protocol. However, the lack of large labeled datasets is still the main challenge in this field. This work provides a detailed study of the applicability of using generative adversarial networks (GANs) algorithms as an augmentation method. Different types of GANs were employed to synthesize HEp-2 cell images to address the data scarcity problem. For systematic comparison, empirical quantitative metrics were implemented to evaluate different GAN models' performance of learning the real data representations. The results of this work showed that though the high visual similarity with the real images, GANs' capacity to generate diverse data is still limited. This deficiency in the generated data diversity is found to be of a crucial impact when used as a standalone method for augmentation. However, combining limited-size GANsgenerated data with classic augmentation improves the classification accuracy across different variants of CNNs. Our results demonstrated a competitive performance for the overall classification accuracy and the mean class accuracy of the HEp-2 cell image classification task.INDEX TERMS Computer-aided diagnosis systems (CADs), Convolutional Neural Networks (CNNs), Data augmentation, Data diversity, Evaluation metrics, Generative adversarial networks (GANs), HEp-2 cell image classification.

show abstract

“…To attain this, they proposed a Teacher-Student training model as well as a unique kind of Soft-Class Activation maps. This scheme permits the discriminator to create weak annotation of the produced images which can be used for automatic annotation of produced images [7].…”

Section: Related Workmentioning

confidence: 99%

Application of Machine Learning in Cryptography

Shende¹

2020

IJATCSE

View full text Add to dashboard Cite

Generally, neural networks have been extremely bad at cryptographic operations as they have a tough time carrying out an easy XOR computation. While that holds true, it ends up that neural networks can protect their private information from other neural networks by discovering unique structure of encryption and decryption, without being taught a specific algorithm. This is a slightly upgraded design used for the paper "Learning to Protect Communications with Adversarial Neural Cryptography". The model used in this paper is coded in python programming language, trained and run on raspberry-pi which provide dedicated hardware for the design.

show abstract

Attention-Aware Generative Adversarial Networks (ATA-GANs)

Cited by 37 publications

References 11 publications

Converting Optical Videos to Infrared Videos Using Attention GAN and Its Impact on Target Detection and Classification Performance

Converting Optical Videos to Infrared Videos Using Attention GAN and Its Impact on Target Detection and Classification Performance

Studying the Applicability of Generative Adversarial Networks on HEp-2 Cell Image Augmentation

Application of Machine Learning in Cryptography

Contact Info

Product

Resources

About