Our blog. Get inspired. Learn more.

Search by tags
Employing Label-Hierarchy to Improve Image Classification
Image classification is one of the most widely tackled tasks in the field of computer vision. It involves predicting one or more relevant labels for a given image. Generally, when performing classification, the various labels are assumed to be independent of each other, which often is not the case and could mean that classification models are missing out on significant improvements in performance. Read on
Global environmental changes pose a serious threat to natural ecosystems. Responding to these threats with effective conservation efforts depends critically on the accurate historical records that are digitised and published by natural history collections. Despite increasing demand for digital access to physical specimens, the number of taxonomic experts working on this process has been declining for several decades. New technologies have the potential for natural history collections to compensate for this shortage of taxonomic expertise and can accelerate the publication of accurate biodiversity data. As a cooperation of ETH Library Lab and the Entomological Collection of ETH Zurich, our Automated Species Identification project aims to develop a practical solution for the classification of specimens based on artificial intelligence and computer vision. Read on

We use cookies to help us give you the best possible user experience on our website. By continuing to browse the site you are agreeing to the use of cookies. More information about privacy can be found here.

Accept