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

Most of the achievements in artificial intelligence so far were accomplishedby supervised learning which requires numerous annotated training data and thuscosts innumerable manpower for labeling. Unsupervised learning is one of theeffective solutions to overcome such difficulties. In our work, we proposeAugNet, a new deep learning training paradigm to learn image features from acollection of unlabeled pictures. We develop a method to construct thesimilarities between pictures as distance metrics in the embedding space byleveraging the inter-correlation between augmented versions of samples. Ourexperiments demonstrate that the method is able to represent the image in lowdimensional space and performs competitively in downstream tasks such as imageclassification and image similarity comparison. Specifically, we achieved over60% and 27% accuracy on the STL10 and CIFAR100 datasets with unsupervisedclustering, respectively. Moreover, unlike many deep-learning-based imageretrieval algorithms, our approach does not require access to externalannotated datasets to train the feature extractor, but still shows comparableor even better feature representation ability and easy-to-use characteristics.In our evaluations, the method outperforms all the state-of-the-art imageretrieval algorithms on some out-of-domain image datasets. The code for themodel implementation is available athttps://github.com/chenmingxiang110/AugNet.

AugNet: End-to-End Unsupervised Visual Representation Learning with Image Augmentation