CoChat
Sign Up
Cited by 1,140

The DOI matches its Crossref record; 6 of the 6 references it cites were found in a registry or an index.

Learning to compare image patches via convolutional neural networks

Zagoruyko, Sergey, Komodakis, Nikos·2015·2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
DOI 10.1109/cvpr.2015.7299064
Open this paper in CoChat — free account

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/cvpr.2015.7299064

Cites

6 of 6 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • A Siamese network has two branches with identical architecture that share parameters during initialization and training, allowing it to learn information from two distributions simultaneously.

    “Siamese network has two branches, each of which have an input and an output (Zagoruyko and Komodakis, 2015). The two branches have an identical architecture and share the same parameters during both initialization and training, which allows the Siamese network to learn information from two distributions simultaneously, as presented in Fig. 7.”

    From Enabling country-scale land cover mapping with meter-resolution satellite imagery (2023) · cites this paper as Zagoruyko and Komodakis, 2015

    Section 3.1 (page not provided) describes a Siamese network with two branches that have identical architecture and share weights; each branch takes one image patch as input and produces an output. It does not say that this arrangement lets the network learn from two distributions simultaneously, or discuss parameter sharing specifically during initialization. (LLM, conf=0.86)

    Experimental — accuracy not yet measured

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Flagged first, then by citations

Research works printed but not linked: 24

  1. fischer, 2014, CoRR
  2. he, 2014, Spatial pyramid pooling in deep convolutional networks for visual recognition, ECCV14, 346
  3. 10.1109/CVPR.2007.383095 · DOI
  4. lecun, 1988, A theoretical framework for back-propagation, Proceedings of the 1988 Connectionist Models Summer School, 21
  5. 10.1109/CVPR.2007.382969 · DOI
  6. 10.1109/CVPRW.2014.131 · DOI · Paper page
  7. 10.1109/TPAMI.2014.2301163 · DOI
  8. zbontar, 2014, Computing the stereo matching cost with a convolutional neural network, CoRR abs/1409 4326
  9. 10.1109/TPAMI.2010.54 · DOI
  10. trzcinski, 2012, Learning Image Descriptors with the Boosting-Trick, NIPS
  11. brown, 2010, Discriminative learning of local image descriptors, IEEE Transactions on Pattern Analysis and Machine Intelligence
  12. 10.1109/CVPR.2005.202 · DOI · Paper page
  13. chetlur, 2014, cudnn: Efficient primitives for deep learning, CoRR abs/1410 0759
  14. conejo, 2014, Inference by learning: Speeding-up graphical model optimization via a coarse-to-fine cascade of pruning classifier, NIPS
  15. collobert, 2011, Torch 7: A matlab-like environment for machine learning, BigLearn NIPS Workshop
  16. eigen, 2014, Depth map prediction from a single image using a multi-scale deep network, NIPS
  17. boix, 2013, Gool. Sparse quantization for patch description, CVPR
  18. simonyan, 2014, Very deep convolutional networks for large-scale image recognition, CoRR abs/1409 1556
  19. 10.1007/s11263-007-0107-3 · DOI
  20. snavely, 2006, Photo tourism: Exploring photo collections in 3d, ACM Trans Graph, 25, 835, 10.1145/1141911.1141964 · DOI
  21. szegedy, 2013, Intriguing properties of neural networks, CoRR abs/1312 6199
  22. 10.1109/CVPR.2008.4587706 · DOI
  23. 10.1109/CVPR.2008.4587673 · DOI
  24. 10.1109/CVPR.2014.220 · DOI · Paper page

Cited by

Sorted by citations

Metadata

Authors
Zagoruyko, S., & Komodakis, N.
Venue
2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Publisher
IEEE
Published
2015-06
Pages
4353-4361
DOI
10.1109/cvpr.2015.7299064
Cited by
1,140
References
6

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review