Fast dense feature extraction with convolutional neural networks that have pooling or striding layers

Christian Bailer, tewodros Habtegebrial, Kiran Varanasi and Didier Stricker

Abstract

In recent years, many publications showed that convolutional neural network based features can have a superior performance to engineered features. However, not much effort was taken so far to extract local features efficiently for a whole image. In this paper, we present an approach to compute patch-based local feature descriptors efficiently in presence of pooling and striding layers for whole images at once. Our approach is generic and can be applied to nearly all existing network architectures. This includes networks for all local feature extraction tasks like camera calibration, Patchmatching, optical flow estimation and stereo matching. In addition, our approach can be applied to other patch-based approaches like sliding window object detection and recognition.

Session

Spotlights

Files

PDF iconPaper (PDF)
PDF iconSupplementary (PDF)
MP4 iconVideo (MP4)

DOI

10.5244/C.31.101
https://dx.doi.org/10.5244/C.31.101

Citation

Christian Bailer, tewodros Habtegebrial, Kiran Varanasi and Didier Stricker. Fast dense feature extraction with convolutional neural networks that have pooling or striding layers. In T.K. Kim, S. Zafeiriou, G. Brostow and K. Mikolajczyk, editors, Proceedings of the British Machine Vision Conference (BMVC), pages 101.1-101.10. BMVA Press, September 2017.

Bibtex

            @inproceedings{BMVC2017_101,
                title={Fast dense feature extraction with convolutional neural networks that have pooling or striding layers},
                author={Christian Bailer, tewodros Habtegebrial, Kiran Varanasi and Didier Stricker},
                year={2017},
                month={September},
                pages={101.1-101.10},
                articleno={101},
                numpages={10},
                booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
                publisher={BMVA Press},
                editor={Tae-Kyun Kim, Stefanos Zafeiriou, Gabriel Brostow and Krystian Mikolajczyk},
                doi={10.5244/C.31.101},
                isbn={1-901725-60-X},
                url={https://dx.doi.org/10.5244/C.31.101}
            }