Semantic Video Segmentation : Exploring Inference Efficiency

September 04, 2015 · Entered Twilight · 🏛 International SoC Design Conference

"Last commit was 9.0 years ago (≥5 year threshold)"

Evidence collected by the PWNC Scanner

Repo contents: .gitignore, CamVid, DenseHO.sdf, DenseHO.sln, DenseHO.suo, DenseHO.vcproj, DenseHO.vcxproj, DenseHO.vcxproj.filters, DenseHO.vcxproj.user, DenseHO_demo.exe, File_format.txt, IL, LICENSE, README.txt, dense_ho_inference.cpp, densecrf.cpp, densecrf.h, fastmath.h, filter.cpp, image.cpp, image.h, ipch, lib64, main.h, permutohedral.cpp, permutohedral.h, probimage.cpp, probimage.h, semantic_segmentation.fig, semantic_segmentation.m, sse_defs.h, std.cpp, std.h, util.cpp, util.h, x64

Authors Subarna Tripathi, Serge Belongie, Youngbae Hwang, Truong Nguyen arXiv ID 1509.02441 Category cs.CV: Computer Vision Citations 26 Venue International SoC Design Conference Repository https://github.com/subtri/video_inference ⭐ 17 Last Checked 1 month ago

Abstract

We explore the efficiency of the CRF inference beyond image level semantic segmentation and perform joint inference in video frames. The key idea is to combine best of two worlds: semantic co-labeling and more expressive models. Our formulation enables us to perform inference over ten thousand images within seconds and makes the system amenable to perform video semantic segmentation most effectively. On CamVid dataset, with TextonBoost unaries, our proposed method achieves up to 8% improvement in accuracy over individual semantic image segmentation without additional time overhead. The source code is available at https://github.com/subtri/video_inference