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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Online continual learning in the wild is a very difficult task in machinelearning. Non-stationarity in online continual learning potentially bringsabout catastrophic forgetting in neural networks. Specifically, onlinecontinual learning for autonomous driving with SODA10M dataset exhibits extraproblems on extremely long-tailed distribution with continuous distributionshift. To address these problems, we propose multiple deep metricrepresentation learning via both contrastive and supervised contrastivelearning alongside soft labels distillation to improve model generalization.Moreover, we exploit modified class-balanced focal loss for sensitivepenalization in class imbalanced and hard-easy samples. We also store somesamples under guidance of uncertainty metric for rehearsal and perform onlineand periodical memory updates. Our proposed method achieves considerablegeneralization with average mean class accuracy (AMCA) 64.01% on validation and64.53% AMCA on test set.

Online Continual Learning via Multiple Deep Metric Learning and  Uncertainty-guided Episodic Memory Replay -- 3rd Place Solution for ICCV 2021  Workshop SSLAD Track 3A Continual Object Classification