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

Class Incremental Learning (CIL) is inspired by the human ability to learnnew classes without forgetting previous ones. CIL becomes more challenging inreal-world scenarios when the samples in each incremental step are imbalanced.This creates another branch of problem, called Generalized Class IncrementalLearning (GCIL) where each incremental step is structured more realistically.Grow When Required (GWR) network, a type of Self-Organizing Map (SOM),dynamically create and remove nodes and edges for adaptive learning. GWRperforms incremental learning from feature vectors extracted by a ConvolutionalNeural Network (CNN), which acts as a feature extractor. The inherent abilityof GWR to form distinct clusters, each corresponding to a class in the featurevector space, regardless of the order of samples or class imbalances, is wellsuited to achieving GCIL. To enhance GWR's classification performance, ahigh-quality feature extractor is required. However, when the convolutionallayers are adapted at each incremental step, the GWR nodes corresponding toprior knowledge are subject to near-invalidation. This work introduces the SelfAugmenting Task Hallucinal Unified Representation (SATHUR), whichre-initializes the GWR network at each incremental step, aligning it with thecurrent feature extractor. Comprehensive experimental results demonstrate thatour proposed method significantly outperforms other state-of-the-art GCILmethods on CIFAR-100 and CORe50 datasets.

SATHUR: Self Augmenting Task Hallucinal Unified Representation for Generalized Class Incremental Learning