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

Recently, deep learning has produced encouraging results for kidney stoneclassification using endoscope images. However, the shortage of annotatedtraining data poses a severe problem in improving the performance andgeneralization ability of the trained model. It is thus crucial to fullyexploit the limited data at hand. In this paper, we propose SegPrompt toalleviate the data shortage problems by exploiting segmentation maps from twoaspects. First, SegPrompt integrates segmentation maps to facilitateclassification training so that the classification model is aware of theregions of interest. The proposed method allows the image and segmentationtokens to interact with each other to fully utilize the segmentation mapinformation. Second, we use the segmentation maps as prompts to tune thepretrained deep model, resulting in much fewer trainable parameters thanvanilla finetuning. We perform extensive experiments on the collected kidneystone dataset. The results show that SegPrompt can achieve an advantageousbalance between the model fitting ability and the generalization ability,eventually leading to an effective model with limited training data.

SegPrompt: Using Segmentation Map as a Better Prompt to Finetune Deep Models for Kidney Stone Classification