CoChat
Sign Up
Cited by 529Domain Adaptation and Few-Shot LearningAdvanced Neural Network ApplicationsAdvanced Image and Video Retrieval Techniques

Towards Open World Recognition

Open access
Bendale, Abhijit, Boult, Terrance·2015·2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
DOI 10.1109/cvpr.2015.7298799
Open this paper in CoChat — free accountOpen PDF

Abstract

With the of advent rich classification models and high computational power visual recognition systems have found many operational applications. Recognition in the real world poses multiple challenges that are not apparent in controlled lab environments. The datasets are dynamic and novel categories must be continuously detected and then added. At prediction time, a trained system has to deal with myriad unseen categories. Operational systems require minimal downtime, even to learn. To handle these operational issues, we present the problem of Open World Recognition and formally define it. We prove that thresholding sums of monotonically decreasing functions of distances in linearly transformed feature space can balance “open space risk” and empirical risk. Our theory extends existing algorithms for open world recognition. We present a protocol for evaluation of open world recognition systems. We present the Nearest Non-Outlier (NNO) algorithm that evolves model efficiently, adding object categories incrementally while detecting outliers and managing open space risk. We perform experiments on the ImageNet dataset with 1.2M+ images to validate the effectiveness of our method on large scale visual recognition tasks. NNO consistently yields superior results on open world recognition.

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.2015.7298799

Cites

Statistics

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?

  • The current dominant machine learning paradigm makes the closed-world assumption, meaning that classes seen in testing or deployment must have been seen during training.

    “The current dominant machine learning paradigm (ML) makes the closedworld assumption , which means that the classes of objects seen by the system in testing or deployment must have been seen during training”

    From Open-world continual learning: Unifying novelty detection and continual learning (2025) · cites this paper as [5]

    The introduction (p. 1) says the closed-world assumption dominates today’s vision systems. Section 5.1 (p. 6) defines closed-set evaluation as using the same classes in training and testing. The cited paper supports the claim for recognition systems, but does not establish that this is the dominant paradigm across machine learning generally. (LLM, conf=0.84)

    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.

Cites

No references could be resolved yet.

Research works printed but not linked: 47

  1. [3][3] P. Bodesheim, A. Freytag, E. Rodner, M. Kemmler, and J. Denzler. Kernel null space methods for novelty detection. In Computer Vision and Pattern Recognition (CVPR), 2013 IEEE Conference on , pages 3374-3381. IEEE, 2013. 1 -
  2. [4][4] G. Cauwenberghs and T. Poggio. Incremental and decremental support vector machine learning. NIPS , 2001. 1, 2 -
  3. [5][5] K. Crammer, O. Dekel, S. Shalev-Shwartz, and Y. Singer. Online passive-aggressive algorithms. JMLR , 2006. 1, 2 -
  4. [6][6] K. Crammer and Y. Singer. On the algorithmic implementations of multiclass kernel-based vector machines. JMLR , 2001. 7 -
  5. [7][7] J. D. Crisman and C. E. Thorpe. Color vision for road following. In 1988 Robotics Conferences , pages 175-185. International Society for Optics and Photonics, 1989. 3 -
  6. [8][8] N. Dalal and B. Triggs. Histogram of oriented gradient for object detection. CVPR , 2005. 10 -
  7. [9][9] P. Datta and D. Kibler. Symbolic nearest mean classifiers. In AAAI/IAAI , pages 82-87, 1997. 3 -
  8. [10][10] T. Dean, M. Ruzon, M. S. J. Shlens, S. Vijayanarasimhan, and J. Yagnik. Fast, accurate detection of 100,000 object classes on a single machine. CVPR , 2013. 1 -
  9. [11][11] J. Deng, S. Satheesh, A. Berg, and L. Fei-Fei. Fast and balanced: Efcient label tree learning for large scale object recognition. NIPS , 2011. 2, 3 -
  10. [12][12] P. Felzenszwalb, R. Girshick, D. McAllester, and D. Ramanan. Object detection with discriminatively trained part based models. IEEE TPAMI , 2010. 10 -
  11. [13][13] V. Fragoso, P. Sen, S. Rodriguez, and M. Turk. Evsac: Accelerating hypotheses generation by modeling matching scores with extreme value theory. ICCV , 2013. 3 -
  12. [14][14] K. Fukunaga. Introduction to statistical pattern recognition . Academic press, 1990. 3 -
  13. [15][15] V. J. Hodge and J. Austin. A survey of outlier detection methodologies. Artificial Intelligence Review , 22(2):85-126, 2004. 1 -
  14. [16][16] L. Jain, W. Scheirer, and T. Boult. Multi-class open set recognition using probability of inclusion. ECCV , 2014. 1, 3, 4, 10 -
  15. [17][17] A. Kapoor, S. Baker, S. Basu, and E. Horvitz. Memory constrained face recognition. CVPR , 2012. 1 -
  16. [18][18] A. Krizhevsky, I. Sutskever, and G. Hinton. Imagenet classification with deep convolutional neural networks. NIPS , 2012. 2 -
  17. [19][19] A. Krizhevsky, I. Sutskever, and G. E. Hinton. Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems , pages 1097-1105, 2012. 1, 6 -
  18. [20][20] L. I. Kuncheva, C. J. Whitaker, and A. Narasimhamurthy. A case-study on na¨ ıve labelling for the nearest mean and the linear discriminant classifiers. Pattern Recognition , 41(10):3010-3020, 2008. 3 -
  19. [21][21] P. Laskov, C. Gehl, S. Kruger, and K. Muller. Incremental support vector learning: Analysis, implementation and applications. JMLR , 2006. 2 -
  20. [22][22] S. Lazebnik, C. Schmid, and J. Ponce. Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. CVPR , 2006. 10 -
  21. [23][23] F. Li and H. Wechsler. Openset face recognition by transduction. IEEE TPAMI , 2005. 2 -
  22. [24][24] L. Li, G. Wang, and L. Fei-Fei. Optimol: automatic online picture collection via incremental MOdel learning. CVPR , 2007. 2, 3 -
  23. [25][25] Y. Lin, F. Lv, S. Zhu, M. Yang, T. Cour, K. Yu, L. Cao, and T. Huang. Large-scale image classification: Fast feature extraction and svm training. CVPR , 2011. 2 -
  24. [26][26] B. Liu, F. Sadeghi, M. Tappen, O. Shamir, and C. Liu. Probabilistic label trees for efficient large scale image classification. CVPR , 2013. 2, 3 -
  25. [27][27] M. Loog. Constrained parameter estimation for semisupervised learning: the case of the nearest mean classifier. In Machine Learning and Knowledge Discovery in Databases , pages 291-304. Springer, 2010. 3 -
  26. [28][28] J. Lu, J. Zhou, J. Wang, T. Mei, X.-S. Hua, and S. Li. Image search results refinement via outlier detection using deep contexts. In Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on , pages 3029-3036. IEEE, 2012. 1 -
  27. [29][29] M. Markou and S. Singh. Novelty detection: a reviewpart 1: statistical approaches. Signal processing , 83(12):24812497, 2003. 1 -
  28. [30][30] M. Marszalek and C. Schmid. Constructing category hierarchies for visual recognition. ECCV , 2008. 2, 3 -
  29. [31][31] T. Mensink, J. Verbeek, F. Perronnin, and G. Csurka. Generalizing to new classes at near zero cost. IEEE TPAMI , 2013. 1, 2, 3, 5, 6 -
  30. [32][32] T. Ojala, M. Pietikainen, and T. Maenpaa. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE TPAMI , 2002. 10 -
  31. [33][33] V. Ordonez, V. Jagadeesh, W. Di, A. Bhardwaj, and R. Piramuthu. Furniture-geek: Understanding fine-grained furniture attributes from freely associated text and tags. WACV , 2014. 1 -
  32. [34][34] F. Perronnin, Z. Akata, Z. Harchaoui, and C. Schmid. Towards good practice in large-scale learning for image classification. In CVPR , pages 3482-3489. IEEE, 2012. 1, 6 -
  33. [36][36] M. Ristin, M. Guillaumin, J. Gall, and L. VanGool. Incremental learning of ncm forests for large scale image classification. CVPR , 2014. 1, 2, 3, 6 -
  34. [38][38] W. Scheirer, L. Jain, and T. Boult. Probability models for open set recognition. IEEE TPAMI , 2014. 1, 3, 4 -
  35. [39][39] W. Scheirer, A. Rocha, A. Sapkota, and T. Boult. Towards open set recognition. IEEE TPAMI , 2013. 1, 2, 3, 4, 6 -
  36. [40][40] P. Sermanet, D. Eigen, Z. Zhang, M. Mathieu, R. Fergus, and Y. LeCun. Overfeat: Integrated recognition, localization and detection using convolutional networks. ICLR , 2014. 5 -
  37. [41][41] S. Shalev-Shwartz, Y. Singer, N. Srebro, and A. Cotter. Pegasos: Primal estimated sub-gradient solver for svm. ICML , 2007. 2 -
  38. [42][42] K. Simonyan, A. Vedaldi, and A. Zisserman. Deep fisher networks for large-scale image classification. NIPS , 2013. 6 -
  39. [43][43] K. Simonyan and A. Zisserman. Very deep convolutional networks for large-scale image recognition. arxiv , 2014. 2 -
  40. [44][44] M. Skurichina and R. P. Duin. Bagging, boosting and the random subspace method for linear classifiers. Pattern Analysis & Applications , 5(2):121-135, 2002. 3 -
  41. [46][46] Y. Taigman, M. Yang, M. Ranzato, and L. Wolf. Deepface: Closing the gap to human-level performance in face verification. CVPR , 2014. 1 -
  42. [47][47] C. J. Veenman and M. J. Reinders. The nearest subclass classifier: A compromise between the nearest mean and nearest neighbor classifier. Pattern Analysis and Machine Intelligence, IEEE Transactions on , 27(9):1417-1429, 2005. 3 -
  43. [48][48] C. J. Veenman and D. M. Tax. A weighted nearest mean classifier for sparse subspaces. In Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on , volume 2, pages 1171-1176. IEEE, 2005. 3 -
  44. [49][49] Z. Wang, K. Crammer, and S. Vucetic. Multi-class pegasos on a budget. ICML , 2010. 2 -
  45. [50][50] Y.-H. Yang, C.-C. Liu, and H. H. Chen. Music emotion classification: a fuzzy approach. In Proceedings of the 14th annual ACM international conference on Multimedia , pages 81-84. ACM, 2006. 3 -
  46. [51][51] T. Yeh and T. Darrell. Dynamic visual category learning. CVPR , 2008. 1, 2, 3 -
  47. [52][52] H. Zhang, A. Berg, M. Maire, and J. Malik. Svm-knn: Discriminative nearest neighbor classification for visual category recognition. CVPR , 2006. 2

Cited by

Sorted by citations

Authors
Bendale, A., & Boult, T.
Affiliations
University of Colorado Colorado Springs (US)
Venue
2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Publisher
IEEE
Published
2015-06
Pages
1893-1902
ISSN
1063-6919 (ISSN-L)
DOI
10.1109/cvpr.2015.7298799
OpenAlex
W1917989004
Cited by
529
References
0
Citations by year
2026: 37 · 2025: 64 · 2024: 93 · 2023: 86 · 2022: 81 · 2021: 59 · 2020: 33 · 2019: 39 · 2018: 16 · 2017: 11 · 2016: 8 · 2015: 2
FWCI
6.83
Type
conference paper
Language
en
Open access
Licence
Locations
  • IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings (publishedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • arXiv (Cornell University)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
Keywords
open-world recognition, open-set recognition, outlier detection, empirical risk, evaluation protocol, ImageNet

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