Learning Placeholders for Open-Set Recognition
Open accessThe DOI matches its Crossref record; 14 of the 14 references it cites were found in a registry or an index.
Abstract
Traditional classifiers are deployed under closed-set setting, with both training and test classes belong to the same set. However, real-world applications probably face the input of unknown categories, and the model will recognize them as known ones. Under such circumstances, open-set recognition is proposed to maintain classification performance on known classes and reject unknowns. The closed-set models make overconfident predictions over familiar known class instances, so that calibration and thresholding across categories become essential issues when extending to an open-set environment. To this end, we proposed to learn PlaceholdeRs for Open-SEt Recognition (Proser), which prepares for the unknown classes by allocating placeholders for both data and classifier. In detail, learning data placeholders tries to anticipate open-set class data, thus transforms closed-set training into open-set training. Besides, to learn the invariant information between target and non-target classes, we reserve classifier placeholders as the class-specific boundary between known and unknown. The proposed Proser efficiently generates novel class by manifold mixup, and adaptively sets the value of reserved open-set classifier during training. Experiments on various datasets validate the effectiveness of our proposed method.
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
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333 · cited 4×
“Since the image size of novel classes does not match CI-FAR10, we design ImageNet-crop, ImageNet-resize, LSUN-crop, and LSUN-resize to align input size.”
MethodInfluentialChandola, V., Banerjee, A., & Kumar, V. (2009) · ACM Computing Surveys · doi:10.1145/1541880.1541882 · Cited by 11,687 · cited 1×
“The problem of out-ofdistribution detection [10, 17, 1], anomaly detection [4, 18, 25] and novelty detection [11, 32, 41, 21, 43] are related topics to open-set recognition.”
BackgroundLiu, F. T., Ting, K. M., & Zhou, Z.-H. (2008) · 2008 Eighth IEEE International Conference on Data Mining · doi:10.1109/icdm.2008.17 · Cited by 6,601 · cited 1×
“The problem of out-ofdistribution detection [10, 17, 1], anomaly detection [4, 18, 25] and novelty detection [11, 32, 41, 21, 43] are related topics to open-set recognition.”
Backgroundmixup: Beyond Empirical Risk Minimization
Zhang, H., Cisse, M., Dauphin, Y. N., & Lopez-Paz, D. (2017) · arXiv · doi:10.48550/arxiv.1710.09412 · Cited by 5,831
A Survey of Outlier Detection Methodologies
Hodge, V., & Austin, J. (2004) · Artificial Intelligence Review · doi:10.1007/s10462-004-4304-y · Cited by 3,596
On calibration of modern neural networks
Guo, C., Pleiss, G., Sun, Y., & Weinberger, K. Q. (2017) · arXiv · doi:10.48550/arxiv.1706.04599 · Cited by 3,435
Deep Learning for Anomaly Detection: A Review
Pang, G., Shen, C., Cao, L., & Hengel, A. V. D. (2022) · ACM Computing Surveys · doi:10.1145/3439950 · Cited by 2,837
Human-level concept learning through probabilistic program induction
Lake, B. M., Salakhutdinov, R., & Tenenbaum, J. B. (2015) · Science · doi:10.1126/science.aab3050 · Cited by 2,817 · cited 3×
“It indicates that open-set recognition on Omniglot and MNIST-noise are more challenging among the three datasets, since they have higher openness than Noise.”
MethodA Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks
Hendrycks, D., & Gimpel, K. (2016) · arXiv · doi:10.48550/arxiv.1610.02136 · Cited by 1,968
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
Towards 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 · cited 2×
“However, this closed-world assumption comes to an end when the test set includes unseen categories [16, 2, 42, 35].”
BackgroundGenerative 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 · cited 3×
“We compare to the SOTA methods, i.e ., Softmax, OpenMax [3], G-OpenMax [6], OSRCI [22], C2AE [24], CROSR [36], GFROSR [26]: Softmax : utilizes the highest softmax probability as the confidence score for detection; OpenMax : replaces softmax layer with OpenMax and cal-ibrates the confidence to predict…”
MethodOpen Category Classification by Adversarial Sample Generation
Yu, Y., Qu, W.-Y., Li, N., & Guo, Z. (2017) · Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2017/469 · Cited by 84 · cited 2×
“Open-set recognition [27, 3, 38, 26] is thus † Correspondence to: Han-Jia Ye (yehj@lamda.nju.edu.cn) proposed to conduct classification on known instances while at the same time detect those from unknown classes.”
BackgroundMethodAdaptive Deep Models for Incremental Learning: Considering Capacity Scalability and Sustainability
Yang, Y., Zhou, D.-W., Zhan, D.-C., Xiong, H., & Jiang, Y. (2019) · Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining · doi:10.1145/3292500.3330865 · Cited by 83 · cited 1×
“Since it is impossible to cover all classes in the world as training set [19, 33], the model would treat all novel category instances as known ones.”
BackgroundSelf-citation
Cited by
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
Class-Incremental Learning: A Survey
Zhou, D.-W., Wang, Q.-W., Qi, Z.-H., Ye, H.-J., Zhan, D.-C., & Liu, Z. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3429383 · Cited by 376
“In DyTox, only task tokens are expanded for each new task, which requires much less memory than saving the whole backbone.”
BackgroundMethodInfluentialSelf-citationFOSTER: Feature Boosting and Compression for Class-Incremental Learning
Wang, F.-Y., Zhou, D.-W., Ye, H.-J., & Zhan, D.-C. (2022) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-19806-9_23 · Cited by 327
Self-citationForward Compatible Few-Shot Class-Incremental Learning
Zhou, D.-W., Wang, F.-Y., Ye, H.-J., Ma, L., Pu, S., & Zhan, D.-C. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00884 · Cited by 281
Self-citationCatching 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
“Out-of-distribution (OOD) detection [17, 18, 20, 29, 43, 68] and open-set recognition [1, 30, 48, 66, 73] are related tasks to ours.”
Background
Metadata
- Authors
- Zhou, D.-W., Ye, H.-J., & Zhan, D.-C.
- Venue
- 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2021-06
- Pages
- 4399-4408
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W3177034761
- Cited by
- 246
- References
- 14
- FWCI
- 20.73
- Type
- conference paper
- Language
- en
- Open access
- green
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.