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

Learning from the web can ease the extreme dependence of deep learning onlarge-scale manually labeled datasets. Especially for fine-grained recognition,which targets at distinguishing subordinate categories, it will significantlyreduce the labeling costs by leveraging free web data. Despite its significantpractical and research value, the webly supervised fine-grained recognitionproblem is not extensively studied in the computer vision community, largelydue to the lack of high-quality datasets. To fill this gap, in this paper weconstruct two new benchmark webly supervised fine-grained datasets, termedWebFG-496 and WebiNat-5089, respectively. In concretely, WebFG-496 consists ofthree sub-datasets containing a total of 53,339 web training images with 200species of birds (Web-bird), 100 types of aircrafts (Web-aircraft), and 196models of cars (Web-car). For WebiNat-5089, it contains 5089 sub-categories andmore than 1.1 million web training images, which is the largest weblysupervised fine-grained dataset ever. As a minor contribution, we also proposea novel webly supervised method (termed "{Peer-learning}") for benchmarkingthese datasets.~Comprehensive experimental results and analyses on two newbenchmark datasets demonstrate that the proposed method achieves superiorperformance over the competing baseline models and states-of-the-art. Ourbenchmark datasets and the source codes of Peer-learning have been madeavailable at{\url{https://github.com/NUST-Machine-Intelligence-Laboratory/weblyFG-dataset}}.

Webly Supervised Fine-Grained Recognition: Benchmark Datasets and An Approach