English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

The recent success of learning-based image rain and noise removal can beattributed primarily to well-designed neural network architectures and largelabeled datasets. However, we discover that current image rain and noiseremoval methods result in low utilization of images. To alleviate the relianceof deep models on large labeled datasets, we propose the task-driven image rainand noise removal (TRNR) based on a patch analysis strategy. The patch analysisstrategy samples image patches with various spatial and statistical propertiesfor training and can increase image utilization. Furthermore, the patchanalysis strategy encourages us to introduce the N-frequency-K-shot learningtask for the task-driven approach TRNR. TRNR allows neural networks to learnfrom numerous N-frequency-K-shot learning tasks, rather than from a largeamount of data. To verify the effectiveness of TRNR, we build a Multi-ScaleResidual Network (MSResNet) for both image rain removal and Gaussian noiseremoval. Specifically, we train MSResNet for image rain removal and noiseremoval with a few images (for example, 20.0\% train-set of Rain100H).Experimental results demonstrate that TRNR enables MSResNet to learn moreeffectively when data is scarce. TRNR has also been shown in experiments toimprove the performance of existing methods. Furthermore, MSResNet trained witha few images using TRNR outperforms most recent deep learning methods traineddata-driven on large labeled datasets. These experimental results haveconfirmed the effectiveness and superiority of the proposed TRNR. The sourcecode is available on \url{https://github.com/Schizophreni/MSResNet-TRNR}.

TRNR: Task-Driven Image Rain and Noise Removal with a Few Images Based on Patch Analysis