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 prediction reliability of neural networks is important in manyapplications. Specifically, in safety-critical domains, such as cancerprediction or autonomous driving, a reliable confidence of model's predictionis critical for the interpretation of the results. Modern deep neural networkshave achieved a significant improvement in performance for many different imageclassification tasks. However, these networks tend to be poorly calibrated interms of output confidence. Temperature scaling is an efficientpost-processing-based calibration scheme and obtains well calibrated results.In this study, we leverage the concept of temperature scaling to build asophisticated bin-wise scaling. Furthermore, we adopt augmentation ofvalidation samples for elaborated scaling. The proposed methods consistentlyimprove calibration performance with various datasets and deep convolutionalneural network models.

Bin-wise Temperature Scaling (BTS): Improvement in Confidence Calibration Performance through Simple Scaling Techniques