Kernelized Subspace Pooling for Deep Local Descriptors
The DOI matches its Crossref record; 8 of the 8 references it cites were found in a registry or an index.
Abstract
Representing local image patches in an invariant and discriminative manner is an active research topic in computer vision. It has recently been demonstrated that local feature learning based on deep Convolutional Neural Network (CNN) can significantly improve the matching performance. Previous works on learning such descriptors have focused on developing various loss functions, regularizations and data mining strategies to learn discriminative CNN representations. Such methods, however, have little analysis on how to increase geometric invariance of their generated descriptors. In this paper, we propose a descriptor that has both highly invariant and discriminative power. The abilities come from a novel pooling method, dubbed Subspace Pooling (SP) which is invariant to a range of geometric deformations. To further increase the discriminative power of our descriptor, we propose a simple distance kernel integrated to the marginal triplet loss that helps to focus on hard examples in CNN training. Finally, we show that by combining SP with the projection distance metric [13], the generated feature descriptor is equivalent to that of the Bilinear CNN model [22], but outperforms the latter with much lower memory and computation consumptions. The proposed method is simple, easy to understand and achieves good performance. Experimental results on several patch matching benchmarks show that our method outperforms the state-of-the-arts significantly.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Distinctive Image Features from Scale-Invariant Keypoints
Lowe, D. G. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000029664.99615.94 · Cited by 55,589
Histograms of Oriented Gradients for Human Detection
Dalal, N., & Triggs, B. (2005) · 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) · doi:10.1109/cvpr.2005.177 · Cited by 33,584
SURF: Speeded Up Robust Features
Bay, H., Tuytelaars, T., & Van Gool, L. (2006) · Lecture Notes in Computer Science · doi:10.1007/11744023_32 · Cited by 14,955 · cited 2×
“[23, 5, 8, 35, 28, 39], while more recent works adopted machine learning methods to learn high-quality feature descriptors from large image datasets [6, 36, 33, 10, 31, 4].”
BackgroundMethodORB-SLAM: A Versatile and Accurate Monocular SLAM System
Mur-Artal, R., Montiel, J. M. M., & Tardos, J. D. (2015) · IEEE Transactions on Robotics · doi:10.1109/tro.2015.2463671 · Cited by 6,778 · cited 1×
“It is often used as an essential step in a wide range of vision tasks such as structure from motion [26], stereo matching [43], image stitching [7], image retrieval [27] and image classification [21], to name a few.”
BackgroundA performance evaluation of local descriptors
Mikolajczyk, K., & Schmid, C. (2005) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2005.188 · Cited by 6,723 · cited 1×
“For example, SIFT [23] and its variants [5, 1] use rectangular regions organized in a grid, GLOH [24] uses a polar arrangement of summing regions, while DAISY [35] employs a set of multi-size circular regions grouped into rings.”
MethodLocal Intensity Order Pattern for feature description
Wang, Z., Fan, B., & Wu, F. (2011) · 2011 International Conference on Computer Vision · doi:10.1109/iccv.2011.6126294 · Cited by 317 · cited 1×
“[23, 5, 8, 35, 28, 39], while more recent works adopted machine learning methods to learn high-quality feature descriptors from large image datasets [6, 36, 33, 10, 31, 4].”
BackgroundHPatches: A benchmark and evaluation of handcrafted and learned local descriptors
Balntas, V., Lenc, K., Vedaldi, A., Tuytelaars, T., Matas, J., & Mikolajczyk, K. (2019) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2915233 · Cited by 132
Cited by
Image Matching from Handcrafted to Deep Features: A Survey
Ma, J., Jiang, X., Fan, A., Jiang, J., & Yan, J. (2021) · International Journal of Computer Vision · doi:10.1007/s11263-020-01359-2 · Cited by 990
Bayesian Loss for Crowd Count Estimation With Point Supervision
Ma, Z., Wei, X., Hong, X., & Gong, Y. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00624 · Cited by 617
Self-citationA review of multimodal image matching: Methods and applications
Jiang, X., Ma, J., Xiao, G., Shao, Z., & Guo, X. (2021) · Information Fusion · doi:10.1016/j.inffus.2021.02.012 · Cited by 532
Image matching across wide baselines: From paper to practice
Jin, Y., Mishkin, D., Mishchuk, A., Matas, J., Fua, P., Yi, K. M., & Trulls, E. (2021) · International Journal of Computer Vision · doi:10.1007/s11263-020-01385-0 · Cited by 388
Topology-Preserving Class-Incremental Learning
Tao, X., Chang, X., Hong, X., Wei, X., & Gong, Y. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58529-7_16 · Cited by 162
Self-citation
Metadata
- Authors
- Wei, X., Zhang, Y., Gong, Y., & Zheng, N.
- Venue
- 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
- Publisher
- IEEE
- Published
- 2018-06
- Pages
- 1867-1875
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W2798314446
- Cited by
- 40
- References
- 8
- FWCI
- 2.23
- Type
- conference paper
- Language
- en
- Open access
- closed
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.