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

This paper addresses incremental few-shot instance segmentation, where a fewexamples of new object classes arrive when access to training examples of oldclasses is not available anymore, and the goal is to perform well on both oldand new classes. We make two contributions by extending the common Mask-RCNNframework in its second stage -- namely, we specify a new object classclassifier based on the probit function and a new uncertainty-guidedbounding-box predictor. The former leverages Bayesian learning to address apaucity of training examples of new classes. The latter learns not only topredict object bounding boxes but also to estimate the uncertainty of theprediction as guidance for bounding box refinement. We also specify two newloss functions in terms of the estimated object-class distribution andbounding-box uncertainty. Our contributions produce significant performancegains on the COCO dataset over the state of the art -- specifically, the gainof +6 on the new classes and +16 on the old classes in the AP instancesegmentation metric. Furthermore, we are the first to evaluate the incrementalfew-shot setting on the more challenging LVIS dataset.

iFS-RCNN: An Incremental Few-shot Instance Segmenter