Digital Repository

Working with Small Datasets

Show simple item record

dc.contributor.advisor Kulkarni, Viraj en_US SETH, JITESH en_US 2021-07-07T03:50:50Z 2021-07-07T03:50:50Z 2021-07
dc.identifier.citation 49 en_US
dc.description.abstract Deep learning semantic segmentation algorithms can localise abnormalities or opacities from chest radiographs. However, collecting and annotating training data is expensive and requires expertise which remains a bottleneck for algorithm performance. We investigate the effect of image augmentations on reducing the requirement of labelled data in the semantic segmentation of chest X-rays for pneumonia detection. We train fully convolutional network models on subsets of different sizes from the total training data. We apply a different image augmentation while training each model and compare it to the baseline trained on the entire dataset without augmentations. We find that rotate and mixup are the best augmentations amongst rotate, mixup, translate, gamma and horizontal flip, wherein they reduce the labelled data requirement by 70% while performing comparably to the baseline in terms of AUC and mean IoU in our experiments. Further, we try a semi-supervised learning approach called pseudo-labelling on the same segmentation model. The approach makes use of unlabelled data and augmentations to enhance the performance of the model. Using the labels of only 8% of the data, we show that it is possible to achieve a similar IoU as the previous experiments. en_US
dc.language.iso en en_US
dc.subject Semantic segmentation en_US
dc.subject Augmentation en_US
dc.subject Chest X-rays en_US
dc.subject Medical image analysis en_US
dc.subject Deep learning en_US
dc.subject Semi-supervised Learning en_US
dc.subject Pseudolabeling en_US
dc.title Working with Small Datasets en_US
dc.type Thesis en_US BS-MS en_US
dc.contributor.department Dept. of Data Science en_US
dc.contributor.registration 20161101 en_US

Files in this item

This item appears in the following Collection(s)

  • MS THESES [1705]
    Thesis submitted to IISER Pune in partial fulfilment of the requirements for the BS-MS Dual Degree Programme/MSc. Programme/MS-Exit Programme

Show simple item record

Search Repository

Advanced Search


My Account