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

The field of Explainable Artificial Intelligence (XAI) aims to improve theinterpretability of black-box machine learning models. Building a heatmap basedon the importance value of input features is a popular method for explainingthe underlying functions of such models in producing their predictions.Heatmaps are almost understandable to humans, yet they are not without flaws.Non-expert users, for example, may not fully understand the logic of heatmaps(the logic in which relevant pixels to the model's prediction are highlightedwith different intensities or colors). Additionally, objects and regions of theinput image that are relevant to the model prediction are frequently notentirely differentiated by heatmaps. In this paper, we propose a frameworkcalled TbExplain that employs XAI techniques and a pre-trained object detectorto present text-based explanations of scene classification models. Moreover,TbExplain incorporates a novel method to correct predictions and textuallyexplain them based on the statistics of objects in the input image when theinitial prediction is unreliable. To assess the trustworthiness and validity ofthe text-based explanations, we conducted a qualitative experiment, and thefindings indicated that these explanations are sufficiently reliable.Furthermore, our quantitative and qualitative experiments on TbExplain withscene classification datasets reveal an improvement in classification accuracyover ResNet variants.

TbExplain: A Text-based Explanation Method for Scene Classification Models with the Statistical Prediction Correction