FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4281694265> ?p ?o ?g. }

• W4281694265 abstract "Abstract Watermark adding is one of the important means for image security and privacy protection in Internet of things (IOT) applications based on federated learning. It is often inseparable from adversarial training with watermark removal algorithms. The effect of watermark removal algorithms will directly affect the final result of watermark addition. However, the existing watermark removal algorithms have drawbacks such as incomplete image watermark removal, poor image quality after watermark removal, large demand for training data, and incorrect filling, which seriously affects the development of image information security and privacy protection in IOT applications based on federated learning. To solve the above problems, this paper proposes an improved image watermark removal convolutional network model based on deep image prior. First, we improve the U‐Net network model, using six downsamping layers and six deconvolution layers combined with deep image prior method to reduce the loss of details and perceive high‐level features, thereby improving the ability of the network to extract high‐level features of the image. In addition, we design a new type of loss function which is called stair loss, and add L1 loss and perception loss to establish new constraints. In order to verify the effectiveness of our method, a comprehensive experimental comparison was conducted on the public dataset PASCAL VOC 2012 in the same experimental environment with CGAN and the deep prior method. The experimental results show that the improved model combined with the deep image prior method can extract the high‐level feature information and can directly remove the watermark from the picture without pretraining the network, the L1 loss and perceptual loss can better retain the image structure information and speed up the watermark removal of the model, the stair loss corrects the final output more accurately by correcting the output of each layer; our method improves the learning ability of the model, and under the condition of the same training time, the image quality after watermark removal is higher, and the final watermark removal result is better, which is more suitable for distributed structure of IoT application based on federated learning." @default.
• W4281694265 created "2022-06-13" @default.
• W4281694265 creator A5015952277 @default.
• W4281694265 creator A5062622010 @default.
• W4281694265 creator A5077519825 @default.
• W4281694265 creator A5081893657 @default.
• W4281694265 creator A5083007404 @default.
• W4281694265 creator A5084708898 @default.
• W4281694265 date "2022-06-01" @default.
• W4281694265 modified "2023-10-15" @default.
• W4281694265 title "An image watermark removal method for secure internet of things applications based on federated learning" @default.
• W4281694265 cites W1483874305 @default.
• W4281694265 cites W2535817897 @default.
• W4281694265 cites W2738361803 @default.
• W4281694265 cites W2766850999 @default.
• W4281694265 cites W2783930095 @default.
• W4281694265 cites W2899380831 @default.
• W4281694265 cites W2906587342 @default.
• W4281694265 cites W2951505650 @default.
• W4281694265 cites W2995187422 @default.
• W4281694265 cites W2995337271 @default.
• W4281694265 cites W3002137088 @default.
• W4281694265 cites W3005641041 @default.
• W4281694265 cites W3014422499 @default.
• W4281694265 cites W3088034552 @default.
• W4281694265 cites W3091074232 @default.
• W4281694265 cites W3120515765 @default.
• W4281694265 cites W3131971504 @default.
• W4281694265 cites W3161325351 @default.
• W4281694265 cites W3168798228 @default.
• W4281694265 cites W3170888612 @default.
• W4281694265 cites W3181787448 @default.
• W4281694265 cites W3185067909 @default.
• W4281694265 cites W3186745756 @default.
• W4281694265 cites W3190219563 @default.
• W4281694265 cites W3201410046 @default.
• W4281694265 cites W3202194958 @default.
• W4281694265 cites W3202810279 @default.
• W4281694265 cites W3208565045 @default.
• W4281694265 cites W3208807485 @default.
• W4281694265 cites W3210971248 @default.
• W4281694265 cites W3212845011 @default.
• W4281694265 cites W3214009653 @default.
• W4281694265 cites W3214309058 @default.
• W4281694265 cites W3214493799 @default.
• W4281694265 cites W3215010342 @default.
• W4281694265 cites W3215141990 @default.
• W4281694265 cites W3215414104 @default.
• W4281694265 cites W3217476834 @default.
• W4281694265 cites W4206707323 @default.
• W4281694265 cites W4212876679 @default.
• W4281694265 cites W4214719528 @default.
• W4281694265 cites W4229439215 @default.
• W4281694265 doi "https://doi.org/10.1111/exsy.13036" @default.
• W4281694265 hasPublicationYear "2022" @default.
• W4281694265 type Work @default.
• W4281694265 citedByCount "0" @default.
• W4281694265 crossrefType "journal-article" @default.
• W4281694265 hasAuthorship W4281694265A5015952277 @default.
• W4281694265 hasAuthorship W4281694265A5062622010 @default.
• W4281694265 hasAuthorship W4281694265A5077519825 @default.
• W4281694265 hasAuthorship W4281694265A5081893657 @default.
• W4281694265 hasAuthorship W4281694265A5083007404 @default.
• W4281694265 hasAuthorship W4281694265A5084708898 @default.
• W4281694265 hasConcept C108583219 @default.
• W4281694265 hasConcept C110875604 @default.
• W4281694265 hasConcept C115961682 @default.
• W4281694265 hasConcept C136764020 @default.
• W4281694265 hasConcept C150817343 @default.
• W4281694265 hasConcept C154945302 @default.
• W4281694265 hasConcept C164112704 @default.
• W4281694265 hasConcept C31972630 @default.
• W4281694265 hasConcept C38652104 @default.
• W4281694265 hasConcept C41008148 @default.
• W4281694265 hasConceptScore W4281694265C108583219 @default.
• W4281694265 hasConceptScore W4281694265C110875604 @default.
• W4281694265 hasConceptScore W4281694265C115961682 @default.
• W4281694265 hasConceptScore W4281694265C136764020 @default.
• W4281694265 hasConceptScore W4281694265C150817343 @default.
• W4281694265 hasConceptScore W4281694265C154945302 @default.
• W4281694265 hasConceptScore W4281694265C164112704 @default.
• W4281694265 hasConceptScore W4281694265C31972630 @default.
• W4281694265 hasConceptScore W4281694265C38652104 @default.
• W4281694265 hasConceptScore W4281694265C41008148 @default.
• W4281694265 hasFunder F4320324173 @default.
• W4281694265 hasIssue "5" @default.
• W4281694265 hasLocation W42816942651 @default.
• W4281694265 hasOpenAccess W4281694265 @default.
• W4281694265 hasPrimaryLocation W42816942651 @default.
• W4281694265 hasRelatedWork W1587163475 @default.
• W4281694265 hasRelatedWork W2019986539 @default.
• W4281694265 hasRelatedWork W2071314500 @default.
• W4281694265 hasRelatedWork W2148446898 @default.
• W4281694265 hasRelatedWork W2367449261 @default.
• W4281694265 hasRelatedWork W2385289568 @default.
• W4281694265 hasRelatedWork W4380927527 @default.
• W4281694265 hasRelatedWork W4385749940 @default.
• W4281694265 hasRelatedWork W887168158 @default.
• W4281694265 hasRelatedWork W2134804386 @default.
• W4281694265 hasVolume "40" @default.

• next