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

Weakly Supervised Semantic Segmentation (WSSS) with image-level labels haslong been suffering from fragmentary object regions led by Class Activation Map(CAM), which is incapable of generating fine-grained masks for semanticsegmentation. To guide CAM to find more non-discriminating object patterns,this paper turns to an interesting working mechanism in agent learning namedComplementary Learning System (CLS). CLS holds that the neocortex builds asensation of general knowledge, while the hippocampus specially learns specificdetails, completing the learned patterns. Motivated by this simple buteffective learning pattern, we propose a General-Specific Learning Mechanism(GSLM) to explicitly drive a coarse-grained CAM to a fine-grained pseudo mask.Specifically, GSLM develops a General Learning Module (GLM) and a SpecificLearning Module (SLM). The GLM is trained with image-level supervision toextract coarse and general localization representations from CAM. Based on thegeneral knowledge in the GLM, the SLM progressively exploits the specificspatial knowledge from the localization representations, expanding the CAM inan explicit way. To this end, we propose the Seed Reactivation to help SLMreactivate non-discriminating regions by setting a boundary for activationvalues, which successively identifies more regions of CAM. Without extrarefinement processes, our method is able to achieve breakthrough improvementsfor CAM of over 20.0% mIoU on PASCAL VOC 2012 and 10.0% mIoU on MS COCO 2014datasets, representing a new state-of-the-art among existing WSSS methods.

Exploit CAM by itself: Complementary Learning System for Weakly Supervised Semantic Segmentation