Segmentation mask and feature similarity loss guided GAN for object-oriented image-to-image translation

Qin, Zhen; Chen, Qingya; Ding, Yi; Zhuang, Tianming; Choo, Kim‐Kwang Raymond

doi:10.1016/j.ipm.2022.102926

Cited by 11 publications

(6 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this paper, we have been inspired by [12, 16] and have added another component to evaluate the similarity of feature maps, which is represented by

{\mathrm{L}}_{{\mathrm{feature}}}^{{\mathrm{x}} \to {\mathrm{y}}}

. This design originated from descriptive capabilities of feature maps.…”

Section: Methodsmentioning

confidence: 99%

“…The image-to-image translation is a kind of image synthesis that learns mapping between two image domains. In this field, there are two types of datasets that affect approaches: paired [1] and unpaired [11][12][13][16][17]. Supervised learning methods are applied in the paired datasets.…”

Section: Image-to-image Translationmentioning

confidence: 99%

“…ObjectVariedGAN [16] was presented to handle geometric content translation. This method provided favorable results when the shapes of the objects differ significantly.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

ARDA‐UNIT recurrent dense self‐attention block with adaptive feature fusion for unpaired (unsupervised) image‐to‐image translation

Ghombavani

Fadaeieslam

2023

IET Image Processing

View full text Add to dashboard Cite

One of the most challenging topics in artificial intelligence is image‐to‐image translation, the purpose of which is generating images close to those in the target domain while preserving the important features of the images in the source domain. In this direction, various types of generative adversarial networks have been developed. ARDA‐UNIT, presented in this paper, seeks to meet the main challenges of these networks, that is, producing a high‐quality image in a reasonable amount of time, and transferring content between two images with different structures. The proposed recurrent dense self‐attention block, applied in ARDA‐UNIT's generator latent space, simultaneously increases its generating capability and decreases the training parameters. ARDA‐UNIT has a feature extraction module which feeds both the generator and the discriminator. This module uses a new adaptive feature fusion method which combines multi‐scale features in such a way that the characteristics of each scale are preserved. The module also uses a pre‐trained CNN that reduces the training parameters. Moreover, a feature similarity loss is introduced that guides the model to change the structure of the source domain in accordance with that in the target domain. Experiments performed on different datasets using FID, KID and IS evaluation criteria have shown that the model reduces computational loads, transfers structures well, and achieves better qualities.

show abstract

“…In this paper, we have been inspired by [12, 16] and have added another component to evaluate the similarity of feature maps, which is represented by

{\mathrm{L}}_{{\mathrm{feature}}}^{{\mathrm{x}} \to {\mathrm{y}}}

. This design originated from descriptive capabilities of feature maps.…”

Section: Methodsmentioning

confidence: 99%

Section: Image-to-image Translationmentioning

confidence: 99%

See 1 more Smart Citation

ARDA‐UNIT recurrent dense self‐attention block with adaptive feature fusion for unpaired (unsupervised) image‐to‐image translation

Ghombavani

Fadaeieslam

2023

IET Image Processing

View full text Add to dashboard Cite

show abstract

“…[1] The path planning algorithm is currently receiving widespread attention. From traditional algorithms to numeration which are integrated with behaviors commonly exist in the world of creatures and smart numerations have come a long way [2] [3]. Different intelligent algorithms have different characteristics, and they differ in the detailed purpose and specific points.…”

Section: Route Arrangement Algorithmmentioning

confidence: 99%

Emergency dispatching method of unmanned vehicle based on shortest path algorithm

Lin

Chen

Cai

2023

3rd International Conference on Applied Mathematics, Modelling, and Intelligent Computing (CAMMIC 2023)

View full text Add to dashboard Cite

The problem of path planning has attracted wide attention. Dispatching is also an extremely essential link in the field of train transportation, especially in the case of emergency, dispatching is more significant. When resolving the dispatching problem, this paper seeks the shortest path based on Dijkstra’s algorithm and sets the functional logic that the dispatching needs to follow. Finally, the experiments indicate that the dispatching method in this paper has achieved excellent outcomes.

show abstract

“…In a watery environment, drones need to avoid obstacles and boats on the water. In addition, in many cases, drones have to dodge obstacles that pop up [4].These potentially dangerous factors are often not recorded in detail or updated in time on the map [6], which brings great hidden dangers to the flight of drones. Thus, it can be seen that how to plan an efficient path quickly and accurately under various scenarios and make it capable of responding to dynamic changes of the scene is a problem that the path planning algorithm should solve.…”

Section: Introductionmentioning

confidence: 99%

Pathfinding algorithm of unmanned aerial vehicle based on deep learning

Lin

Chen

Zhu

2023

3rd International Conference on Artificial Intelligence, Automation, and High-Performance Computing (AIAHPC 2023)

View full text Add to dashboard Cite

Pathfinding algorithm has a decisive impact on unmanned aerial vehicle flight. In practical applications, aerial vehicle is often required to respond to emergencies quickly and plan a new path in time. Therefore, we designed a pathfinding optimization algorithm, combined with the object detection algorithm based on deep learning network, to identify objects that suddenly appear on the original path, timely avoid and re-plan the path. Experiments show that the proposed method can re-plan the new safe path in a short time which satisfies the requirements in response time and path planning.

show abstract

Segmentation mask and feature similarity loss guided GAN for object-oriented image-to-image translation

Cited by 11 publications

References 27 publications

ARDA‐UNIT recurrent dense self‐attention block with adaptive feature fusion for unpaired (unsupervised) image‐to‐image translation

ARDA‐UNIT recurrent dense self‐attention block with adaptive feature fusion for unpaired (unsupervised) image‐to‐image translation

Emergency dispatching method of unmanned vehicle based on shortest path algorithm

Pathfinding algorithm of unmanned aerial vehicle based on deep learning

Contact Info

Product

Resources

About