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 Plus annual

Presents the access of premium content as premium feature

Premium Content

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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

We propose a dynamic filtering strategy with large sampling field forConvNets (LS-DFN), where the position-specific kernels learn from not only theidentical position but also multiple sampled neighbor regions. During sampling,residual learning is introduced to ease training and an attention mechanism isapplied to fuse features from different samples. Such multiple samples enlargethe kernels' receptive fields significantly without requiring more parameters.While LS-DFN inherits the advantages of DFN, namely avoiding feature mapblurring by position-wise kernels while keeping translation invariance, it alsoefficiently alleviates the overfitting issue caused by much more parametersthan normal CNNs. Our model is efficient and can be trained end-to-end viastandard back-propagation. We demonstrate the merits of our LS-DFN on bothsparse and dense prediction tasks involving object detection, semanticsegmentation, and flow estimation. Our results show LS-DFN enjoys strongerrecognition abilities in object detection and semantic segmentation tasks onVOC benchmark and sharper responses in flow estimation on FlyingChairs datasetcompared to strong baselines.

Dynamic Filtering with Large Sampling Field for ConvNets