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

This paper proposes an automatic image co-segmentation algorithm based ondeep reinforcement learning (RL). Existing co-segmentation tasks mainly rely ondeep learning methods, and the obtained foreground edges are often rough. Inorder to obtain more precise foreground edges, we use deep RL to solve thisproblem and achieve the finer segmentation. To our best knowledge, this is thefirst work to apply RL methods to co-segmentation. We define the problem as aMarkov Decision Process (MDP) and optimize it by RL with asynchronous advantageactor-critic (A3C). The RL image co-segmentation network uses the correlationbetween images to segment common and salient objects from a set of relatedimages. In order to achieve automatic segmentation, our RL-CoSeg methodeliminates user's hints. For the image co-segmentation problem, we propose acollaborative RL algorithm based on the A3C model. We propose a Siamese RLco-segmentation network structure to obtain the co-attention of images forco-segmentation. We improve the self-attention for automatic RL algorithm toobtain long-distance dependence and enlarge the receptive field. The imagefeature information obtained by self-attention can be used to supplement thedeleted user's hints and help to obtain more accurate actions. Experimentalresults have shown that our method can improve the performance effectively onboth coarse and fine initial segmentations, and it achieves thestate-of-the-art performance on Internet dataset, iCoseg dataset and MLMR-COSdataset.

RL-CoSeg : A Novel Image Co-Segmentation Algorithm with Deep Reinforcement Learning