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

In this work, the case of semantic segmentation on a small image dataset(simulated by 1000 randomly selected images from PASCAL VOC 2012), where onlyweak supervision signals (scribbles from user interaction) are available isstudied. Especially, to tackle the problem of limited data annotations in imagesegmentation, transferring different pre-trained models and CRF based methodsare applied to enhance the segmentation performance. To this end, RotNet,DeeperCluster, and Semi&Weakly Supervised Learning (SWSL) pre-trained modelsare transferred and finetuned in a DeepLab-v2 baseline, and dense CRF isapplied both as a post-processing and loss regularization technique. Theresults of my study show that, on this small dataset, using a pre-trainedResNet50 SWSL model gives results that are 7.4% better than applying anImageNet pre-trained model; moreover, for the case of training on the fullPASCAL VOC 2012 training data, this pre-training approach increases the mIoUresults by almost 4%. On the other hand, dense CRF is shown to be veryeffective as well, enhancing the results both as a loss regularizationtechnique in weakly supervised training and as a post-processing tool.

Tackling the Problem of Limited Data and Annotations in Semantic Segmentation