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

By leveraging deep learning to automatically classify camera trap images,ecologists can monitor biodiversity conservation efforts and the effects ofclimate change on ecosystems more efficiently. Due to the imbalancedclass-distribution of camera trap datasets, current models are biased towardsthe majority classes. As a result, they obtain good performance for a fewmajority classes but poor performance for many minority classes. We usedtwo-phase training to increase the performance for these minority classes. Wetrained, next to a baseline model, four models that implemented a differentversions of two-phase training on a subset of the highly imbalanced SnapshotSerengeti dataset. Our results suggest that two-phase training can improveperformance for many minority classes, with limited loss in performance for theother classes. We find that two-phase training based on majority undersamplingincreases class-specific F1-scores up to 3.0%. We also find that two-phasetraining outperforms using only oversampling or undersampling by 6.1% inF1-score on average. Finally, we find that a combination of over- andundersampling leads to a better performance than using them individually.

Two-phase training mitigates class imbalance for camera trap image classification with CNNs