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

State-of-the-art (SOTA) anomaly segmentation approaches on complex urbandriving scenes explore pixel-wise classification uncertainty learned fromoutlier exposure, or external reconstruction models. However, previousuncertainty approaches that directly associate high uncertainty to anomaly maysometimes lead to incorrect anomaly predictions, and external reconstructionmodels tend to be too inefficient for real-time self-driving embedded systems.In this paper, we propose a new anomaly segmentation method, named pixel-wiseenergy-biased abstention learning (PEBAL), that explores pixel-wise abstentionlearning (AL) with a model that learns an adaptive pixel-level anomaly class,and an energy-based model (EBM) that learns inlier pixel distribution. Morespecifically, PEBAL is based on a non-trivial joint training of EBM and AL,where EBM is trained to output high-energy for anomaly pixels (from outlierexposure) and AL is trained such that these high-energy pixels receive adaptivelow penalty for being included to the anomaly class. We extensively evaluatePEBAL against the SOTA and show that it achieves the best performance acrossfour benchmarks. Code is available at https://github.com/tianyu0207/PEBAL.

Pixel-wise Energy-biased Abstention Learning for Anomaly Segmentation on Complex Urban Driving Scenes