Weakly Supervised Graph Propagation Towards Collective Image Parsing


In this work, we propose a weakly supervised graph propagation method to automatically assign the annotated labels at image level to those contextually derived semantic regions. The graph is constructed with the over-segmented patches of the image collection as nodes. Image-level labels are imposed on the graph as weak supervision information over subgraphs, each of which corresponds to all patches of one image, and the contextual information across different images at patch level are then mined to assist the process of label propagation from images to their descendent regions. The ultimate optimization problem is efficiently solved by Convex Concave Programming (CCCP). Extensive experiments on four benchmark datasets clearly demonstrate the effectiveness of our proposed method for the task of collective image parsing. Two extensions including image annotation and concept map based image retrieval demonstrate the proposed image parsing algorithm can effectively aid other vision tasks.

Did you like this research project?

To get this research project Guidelines, Training and Code... Click Here

PROJECT TITLE :Exploring Weakly Labeled Images for Video Object Segmentation With Submodular Proposal Selection - 2018ABSTRACT:Video object segmentation (VOS) is important for numerous computer vision issues, and handling it
PROJECT TITLE :Narrowband Reflection From Weakly Coupled Cladding-Modulated Bragg GratingsABSTRACT:A complementary metal-oxide-semiconductor-compatible cladding-modulated grating style with weakly coupled corrugations on long
PROJECT TITLE :An Acceleration Sensing Method Based on the Mode Localization of Weakly Coupled ResonatorsABSTRACT:This paper reports an acceleration sensing technique based mostly on 2 weakly coupled resonators (WCRs) using the
PROJECT TITLE :Semantic Annotation of High-Resolution Satellite Images via Weakly Supervised LearningABSTRACT:During this paper, we tend to specialise in tackling the problem of automatic semantic annotation of high resolution
PROJECT TITLE :One-step leapfrog weakly conditionally stable finite-difference time-domain method for body of revolutionABSTRACT:During this study, a completely unique one-step leapfrog weakly conditionally stable finite-difference

Ready to Complete Your Academic MTech Project Work In Affordable Price ?

Project Enquiry