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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Finding general evaluation metrics for unsupervised representation learningtechniques is a challenging open research question, which recently has becomemore and more necessary due to the increasing interest in unsupervised methods.Even though these methods promise beneficial representation characteristics,most approaches currently suffer from the objective function mismatch. Thismismatch states that the performance on a desired target task can decrease whenthe unsupervised pretext task is learned too long - especially when both tasksare ill-posed. In this work, we build upon the widely used linear evaluationprotocol and define new general evaluation metrics to quantitatively capturethe objective function mismatch and the more generic metrics mismatch. Wediscuss the usability and stability of our protocols on a variety of pretextand target tasks and study mismatches in a wide range of experiments. Therebywe disclose dependencies of the objective function mismatch across severalpretext and target tasks with respect to the pretext model's representationsize, target model complexity, pretext and target augmentations as well aspretext and target task types. In our experiments, we find that the objectivefunction mismatch reduces performance by ~0.1-5.0% for Cifar10, Cifar100 andPCam in many setups, and up to ~25-59% in extreme cases for the 3dshapesdataset.

Don't miss the Mismatch: Investigating the Objective Function Mismatch for Unsupervised Representation Learning