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

Data augmentation is usually adopted to increase the amount of training data,prevent overfitting and improve the performance of deep models. However, inpractice, random data augmentation, such as random image cropping, islow-efficiency and might introduce many uncontrolled background noises. In thispaper, we propose Weakly Supervised Data Augmentation Network (WS-DAN) toexplore the potential of data augmentation. Specifically, for each trainingimage, we first generate attention maps to represent the object'sdiscriminative parts by weakly supervised learning. Next, we augment the imageguided by these attention maps, including attention cropping and attentiondropping. The proposed WS-DAN improves the classification accuracy in twofolds. In the first stage, images can be seen better since more discriminativeparts' features will be extracted. In the second stage, attention regionsprovide accurate location of object, which ensures our model to look at theobject closer and further improve the performance. Comprehensive experiments incommon fine-grained visual classification datasets show that our WS-DANsurpasses the state-of-the-art methods, which demonstrates its effectiveness.

See Better Before Looking Closer: Weakly Supervised Data Augmentation Network for Fine-Grained Visual Classification