Towards Open Set Deep Networks
Open accessAbstract
Deep networks have produced significant gains for various visual recognition problems, leading to high impact academic and commercial applications. Recent work in deep networks highlighted that it is easy to generate images that humans would never classify as a particular object class, yet networks classify such images high confidence as that given class - deep network are easily fooled with images humans do not consider meaningful. The closed set nature of deep networks forces them to choose from one of the known classes leading to such artifacts. Recognition in the real world is open set, i.e. the recognition system should reject unknown/unseen classes at test time. We present a methodology to adapt deep networks for open set recognition, by introducing a new model layer, OpenMax, which estimates the probability of an input being from an unknown class. A key element of estimating the unknown probability is adapting Meta-Recognition concepts to the activation patterns in the penultimate layer of the network. Open-Max allows rejection of "fooling" and unrelated open set images presented to the system, OpenMax greatly reduces the number of obvious errors made by a deep network. We prove that the OpenMax concept provides bounded open space risk, thereby formally providing an open set recognition solution. We evaluate the resulting open set deep networks using pre-trained networks from the Caffe Model-zoo on ImageNet 2012 validation data, and thousands of fooling and open set images. The proposed OpenMax model significantly outperforms open set recognition accuracy of basic deep networks as well as deep networks with thresholding of SoftMax probabilities.
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.
Integrity signals
Registry
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.
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?
Particular challenges for animal re-identification in wild populations include difficulty of manual curation, larger populations, changes in appearance, few sightings per individual, and frequent addition of new individuals, creating an open-set problem.
“The particular challenges for animal (re-)identification in wild populations are related to the difficulty of manual curation, larger populations, changes in appearance (e.g., due to scars, growth), few sightings per individual, and the frequent addition of new individuals that may enter the system due to birth or immigration, therefore creating an “open-set” problem104 wherein the model must deal”
From Perspectives in machine learning for wildlife conservation (2022) · cites this paper as [104]
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
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · see citing works
Going deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562 · see citing works
ImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380 · see citing works
Caffe: Convolutional Architecture for Fast Feature Embedding
Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., & Darrell, T. (2014) · Proceedings of the 22nd ACM international conference on Multimedia · doi:10.1145/2647868.2654889 · Cited by 11,077 · see citing works
Explaining and Harnessing Adversarial Examples
Goodfellow, I. J., Shlens, J., & Szegedy, C. (2014) · arXiv · doi:10.48550/arxiv.1412.6572 · Cited by 10,381 · see citing works
DeepFace: Closing the Gap to Human-Level Performance in Face Verification
Taigman, Y., Yang, M., Ranzato, M., & Wolf, L. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.220 · Cited by 6,542 · see citing works
Caffe: Convolutional Architecture for Fast Feature EmbeddingPreprint
Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., & Darrell, T. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1408.5093 · Cited by 4,748 · see citing works
Return of the Devil in the Details: Delving Deep into Convolutional Nets
Chatfield, K., Simonyan, K., Vedaldi, A., & Zisserman, A. (2014) · Proceedings of the British Machine Vision Conference 2014 · doi:10.5244/c.28.6 · Cited by 3,335 · see citing works
Deep neural networks are easily fooled: High confidence predictions for unrecognizable images
Nguyen, A., Yosinski, J., & Clune, J. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298640 · Cited by 3,258 · see citing works
Diagnosis of multiple cancer types by shrunken centroids of gene expression
Tibshirani, R. J., Hastie, T. J., Narasimhan, B., & Chu, G. (2002) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.082099299 · Cited by 2,938 · see citing works
Understanding Neural Networks Through Deep VisualizationPreprint
Yosinski, J., Clune, J., Nguyen, A. M., Fuchs, T. J., & Lipson, H. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1506.06579 · Cited by 1,687 · see citing works
Scheirer, W. J., de Rezende Rocha, A., Sapkota, A., & Boult, T. E. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2012.256 · Cited by 1,573 · see citing works
Self-citationFrom captions to visual concepts and back
Fang, H., Gupta, S., Iandola, F., Srivastava, R. K., Deng, L., Dollár, P., Gao, J., He, X., Mitchell, M., Platt, J. C., et al. (2015) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2015.7298754 · Cited by 1,305 · see citing works
Zero-Shot Learning Through Cross-Modal Transfer
Socher, R., Ganjoo, M., Sridhar, H., Bastani, O., Manning, C. D., & Ng, A. Y. (2013) · arXiv · doi:10.48550/arxiv.1301.3666 · Cited by 997 · see citing works
Is object localization for free? - Weakly-supervised learning with convolutional neural networks
Oquab, M., Bottou, L., Laptev, I., & Sivic, J. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298668 · Cited by 886 · see citing works
Probability Models for Open Set Recognition
Scheirer, W. J., Jain, L. P., & Boult, T. E. (2014) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2014.2321392 · Cited by 630 · see citing works
Self-citationTowards Open World Recognition
Bendale, A., & Boult, T. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298799 · Cited by 529 · see citing works
Self-citationDistance-Based Image Classification: Generalizing to New Classes at Near-Zero Cost
Mensink, T., Verbeek, J. J., Perronnin, F., & Csurka, G. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2013.83 · Cited by 426 · see citing works
Fast, Accurate Detection of 100,000 Object Classes on a Single Machine
Dean, T., Ruzon, M. A., Segal, M., Shlens, J., Vijayanarasimhan, S., & Yagnik, J. (2013) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2013.237 · Cited by 307 · see citing works
Towards Open World Recognition
Bendale, A., & Boult, T. E. (2016) · Cited by 287 · see citing works
Self-citationMetric Learning for Large Scale Image Classification: Generalizing to New Classes at Near-Zero Cost
Mensink, T., Verbeek, J., Perronnin, F., & Csurka, G. (2012) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-33709-3_35 · Cited by 281 · see citing works
Meta-Recognition: The Theory and Practice of Recognition Score Analysis
Scheirer, W., Rocha, A., Micheals, R., et al. (2011) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2011.54 · Cited by 220 · see citing works
Garrow, D. (2017) · The SHAFR Guide Online · doi:10.1163/2468-1733_shafr_sim260030022 · Cited by 155 · see citing works
Predicting Failures of Vision Systems
Zhang, P., Wang, J., Farhadi, A., Hebert, M., & Parikh, D. (2014) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2014.456 · Cited by 124 · see citing works
Learning with Augmented Class by Exploiting Unlabeled Data
Da, Q., Yang, Y., & Zhou, Z. (2014) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v28i1.8997 · Cited by 89 · see citing works
Incremental Learning of NCM Forests for Large-Scale Image Classification
Ristin, M., Guillaumin, M., Gall, J., & Van Gool, L. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.467 · Cited by 82 · see citing works
Local Novelty Detection in Multi-class Recognition Problems
Bodesheim, P., Freytag, A., Rodner, E., & Denzler, J. (2015) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv.2015.113 · Cited by 55 · see citing works
Has My Algorithm Succeeded? An Evaluator for Human Pose Estimators
Jammalamadaka, N., Zisserman, A., Eichner, M. L., et al. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-33712-3_9 · Cited by 39 · see citing works
Furniture-geek: Understanding fine-grained furniture attributes from freely associated text and tags
Ordóñez, V., Jagadeesh, V., Wei, D., et al. (2014) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv.2014.6836083 · Cited by 8 · see citing works
Flagged first, then by citations
Research works printed but not linked: 5
- [7][7] A. Frome, G. S. Corrado, J. Shlens, S. Bengio, J. Dean, T. Mikolov, et al. Devise: A deep visual-semantic embed- Figure 7: The graphs shows F-Measure performance of OpenMax and Softmax with Open Set testing (using validation, fooling and open set images for testing). Each graph shows F-measure plotted against varying uncertainty threshold values. Tail size varies in different plots. OpenMax reaches its optimal performance at tail size 20. For tail sizes larger than 20, though OpenMax becomes good at rejecting images from fooling set and open set (Fig 6), it also rejects true images thus reducing accuracy on validation set. Hence, we choose tail size 20 for our experiments in main paper. <!-- image --> Figure 8: The above figure shows performance of OpenMax and Softmax as number of top classes to be considered for recalibrating are changed. In our experiments, we found best performance when top 10 classes (i.e. α = 10 ) were considered for recalibration. <!-- image --> ding model. In Advances in Neural Information Processing Systems , pages 2121-2129, 2013. 8 -
- [23][23] K. Simonyan and A. Zisserman. Very deep convolutional networks for large scale image recognition. In International Conference on Learning Representations . Computational and Biological Learning Society, 2015. 7 -
- [25][25] R. Socher, C. D. Manning, and A. Y. Ng. Learning continuous phrase representations and syntactic parsing with recursive neural networks. In Proceedings of the NIPS-2010 Deep Learning and Unsupervised Feature Learning Work- 1000 Figure 13: The above figure shows confusion matrix of distances between Mean Activation Vector (MAV) for each class in ILSVRC 2012 with MAV of every other class. Lower values of distances indicate that MAVs for respective classes are very close to each other, and higher values of distances indicate classes that are far apart. Majority of misclassifications for OpenMax happen in fine-grained categorization, which is to be expected. <!-- image --> shop , pages 1-9, 2010. 1, 7 -
- [27][27] C. Szegedy, W. Zaremba, I. Sutskever, J. Bruna, D. Erhan, I. Goodfellow, and R. Fergus. Intriguing properties of neural networks. In International Conference on Learning Representations . Computational and Biological Learning Society, 2014. 2, 4, 5 -
- [30][30] A. Vezhnevets and V. Ferrari. Object localization in imagenet by looking out of the window. In Proceedings of the British Machine Vision Conference,(BMVC) , 2015. 8 -
Cited by
Sorted by citations
Zero-Shot Learning—A Comprehensive Evaluation of the Good, the Bad and the Ugly
Xian, Y., Lampert, C. H., Schiele, B., & Akata, Z. (2019) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2018.2857768 · Cited by 1,678 · see citing works
BranchyNet: Fast inference via early exiting from deep neural networks
Teerapittayanon, S., McDanel, B., & Kung, H. T. (2016) · 2016 23rd International Conference on Pattern Recognition (ICPR) · doi:10.1109/icpr.2016.7900006 · Cited by 1,326 · see citing works
Perspectives in machine learning for wildlife conservation
Tuia, D., Kellenberger, B., Beery, S., Costelloe, B. R., Zuffi, S., Risse, B., Mathis, A., Mathis, M. W., van Langevelde, F., Burghardt, T., et al. (2022) · Nature Communications · doi:10.1038/s41467-022-27980-y · Cited by 740 · see citing works
Generalized Out-of-Distribution Detection: A Survey
Yang, J., Zhou, K., Li, Y., & Liu, Z. (2024) · International Journal of Computer Vision · doi:10.1007/s11263-024-02117-4 · Cited by 884 · see citing works
Generalized ODIN: Detecting Out-of-Distribution Image Without Learning From Out-of-Distribution Data
Hsu, Y.-C., Shen, Y., Jin, H., & Kira, Z. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01096 · Cited by 499 · see citing works
Generative OpenMax for Multi-Class Open Set Classification
Ge, Z., Demyanov, S., & Garnavi, R. (2017) · Procedings of the British Machine Vision Conference 2017 · doi:10.5244/c.31.42 · Cited by 472 · see citing works
“However, we perfomed the same experiment as in [3] and figured out there are no obvious performance improvement by using G-OpenMax over the natural image setting.”
BackgroundMethodInfluentialCatching Both Gray and Black Swans: Open-set Supervised Anomaly Detection
Ding, C., Pang, G., & Shen, C. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00724 · Cited by 197 · see citing works
Detecting unexpected obstacles for self-driving cars: Fusing deep learning and geometric modeling
Ramos, S., Gehrig, S., Pinggera, P., Franke, U., & Rother, C. (2017) · 2017 IEEE Intelligent Vehicles Symposium (IV) · doi:10.1109/ivs.2017.7995849 · Cited by 170 · see citing works
Applications and Challenges of Artificial Intelligence in Space Missions
Oche, P. A., Ewa, G. A., & Ibekwe, N. (2024) · IEEE Access · doi:10.1109/access.2021.3132500 · Cited by 68 · see citing works
“For instance, under the learning axis, ―Identifying Unknowns‖ is a key challenge because of the common assumption in DL that trained models will be deployed under closed-set conditions [241] .”
Background
- Authors
- Bendale, A., & Boult, T. E.
- Affiliations
- University of Colorado Colorado Springs (US)
- ORCID
- Boult, Terrance E.
- Venue
- 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2016-06
- Pages
- 1563-1572
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W2272331516
- Cited by
- 1,799
- References
- 29
- Citations by year
- 2026: 213 · 2025: 274 · 2024: 275 · 2023: 298 · 2022: 210 · 2021: 226 · 2020: 124 · 2019: 93 · 2018: 58 · 2017: 24 · 2016: 4
- FWCI
- 20.42
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- 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 › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Keywords
- open-set recognition, OpenMax, deep neural network, unknown class detection, image classification
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
