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

Semantic segmentation has achieved huge progress via adopting deep FullyConvolutional Networks (FCN). However, the performance of FCN based modelsseverely rely on the amounts of pixel-level annotations which are expensive andtime-consuming. To address this problem, it is a good choice to learn tosegment with weak supervision from bounding boxes. How to make full use of theclass-level and region-level supervisions from bounding boxes is the criticalchallenge for the weakly supervised learning task. In this paper, we firstintroduce a box-driven class-wise masking model (BCM) to remove irrelevantregions of each class. Moreover, based on the pixel-level segment proposalgenerated from the bounding box supervision, we could calculate the meanfilling rates of each class to serve as an important prior cue, then we proposea filling rate guided adaptive loss (FR-Loss) to help the model ignore thewrongly labeled pixels in proposals. Unlike previous methods directly trainingmodels with the fixed individual segment proposals, our method can adjust themodel learning with global statistical information. Thus it can help reduce thenegative impacts from wrongly labeled proposals. We evaluate the proposedmethod on the challenging PASCAL VOC 2012 benchmark and compare with othermethods. Extensive experimental results show that the proposed method iseffective and achieves the state-of-the-art results.

Box-driven Class-wise Region Masking and Filling Rate Guided Loss for Weakly Supervised Semantic Segmentation