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/

Zendy Plus

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

Zendy Tools

Zendy Open

We propose a lightweight, single image super-resolution network for mobiledevices, named XCAT. XCAT introduces Heterogeneous Group Convolution Blockswith Cross Concatenations (HXBlock). The heterogeneous split of the inputchannels to the group convolution blocks reduces the number of operations, andcross concatenation allows for information flow between the intermediate inputtensors of cascaded HXBlocks. Cross concatenations inside HXBlocks can alsoavoid using more expensive operations like 1x1 convolutions. To further prevent expensive tensor copy operations, XCAT utilizes non-trainable convolutionkernels to apply up sampling operations. Designed with integer quantization inmind, XCAT also utilizes several techniques on training, like intensity-baseddata augmentation. Integer quantized XCAT operates in real time on Mali-G71 MP2GPU with 320ms, and on Synaptics Dolphin NPU with 30ms (NCHW) and 8.8ms (NHWC),suitable for real-time applications.

XCAT -- Lightweight Quantized Single Image Super-Resolution using Heterogeneous Group Convolutions and Cross Concatenation