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

Recently, DNN model compression based on network architecture design, e.g.,SqueezeNet, attracted a lot attention. No accuracy drop on image classificationis observed on these extremely compact networks, compared to well-known models.An emerging question, however, is whether these model compression techniqueshurt DNN's learning ability other than classifying images on a single dataset.Our preliminary experiment shows that these compression methods could degradedomain adaptation (DA) ability, though the classification performance ispreserved. Therefore, we propose a new compact network architecture andunsupervised DA method in this paper. The DNN is built on a new basic moduleConv-M which provides more diverse feature extractors without significantlyincreasing parameters. The unified framework of our DA method willsimultaneously learn invariance across domains, reduce divergence of featurerepresentations, and adapt label prediction. Our DNN has 4.1M parameters, whichis only 6.7% of AlexNet or 59% of GoogLeNet. Experiments show that our DNNobtains GoogLeNet-level accuracy both on classification and DA, and our DAmethod slightly outperforms previous competitive ones. Put all together, our DAstrategy based on our DNN achieves state-of-the-art on sixteen of totaleighteen DA tasks on popular Office-31 and Office-Caltech datasets.

A Compact DNN: Approaching GoogLeNet-Level Accuracy of Classification and Domain Adaptation