research-article
Authors: Zijian Liu, Yaning Wang, Yang Luo, and Chunbo Luo
Volume 154, Issue C
Published: 02 July 2024 Publication History
- 0citation
- 0
- Downloads
Metrics
Total Citations0Total Downloads0Last 12 Months0
Last 6 weeks0
New Citation Alert added!
This alert has been successfully added and will be sent to:
You will be notified whenever a record that you have chosen has been cited.
To manage your alert preferences, click on the button below.
Manage my Alerts
New Citation Alert!
Please log in to your account
- View Options
- References
- Media
- Tables
- Share
Abstract
Few-shot learning, a promising technique for acquiring new concepts from limited data, assumes that testing samples belong to “unknown classes” and are regarded as new knowledge. However, real-world scenarios introduce uncertainty about the class membership of testing samples. To address this uncertainty, we propose a novel challenge of few-shot incremental unknown class detection, aligning more closely with practical situations. Open set recognition can classify known class samples and reject unknown class samples to mitigate the uncertainty, but it struggles to address the critical limitation of having few available samples. To tackle both uncertainty and limitation, we propose a graph-based few-shot incremental learning algorithm for unknown class detection, which includes four components. First, a feature extractor learns from the base dataset during training and is subsequently fixed for embedding node features from the novel dataset during inference. Then, embedded node features, along with their corresponding prototypes, contribute to graph generation and edge construction. Third, a mixed-rejection strategy is proposed to determine the class membership of testing samples. Finally, a novel class is treated as a new known class, engaging the embedded node features in graph update and edge reconstruction. Evaluation on benchmark datasets with varying structures, including USTC-TFC2016 and miniImageNet datasets, demonstrates that our proposed algorithm outperforms classical open set recognition algorithm in few-shot incremental learning for unknown class detection, which offers promising performance and potential for practical applications in real-world scenarios.
Highlights
•
Introduce few-shot incremental learning (FSIL) for unknown class detection.
•
Propose the graph-based FSIL algorithm for unknown class detection.
•
The proposed algorithm outperforms the baselines on two benchmark datasets.
References
[1]
T. He, Z. Zhang, H. Zhang, Z. Zhang, J. Xie, M. Li, Bag of tricks for image classification with convolutional neural networks, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, USA, 2019, pp. 558–567.
[2]
A. Krizhevsky, I. Sutskever, G.E. Hinton, Imagenet classification with deep convolutional neural networks, in: Advances in Neural Information Processing Systems, Harrahs and Harveys, USA, 2012, pp. 1097–1105.
[3]
H. Hu, J. Gu, Z. Zhang, J. Dai, Y. Wei, Relation networks for object detection, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, USA, 2018, pp. 3588–3597.
[4]
R. Girshick, Fast r-cnn, in: Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile, 2015, pp. 1440–1448.
[5]
Garcia-Garcia A., Orts-Escolano S., Oprea S., Villena-Martinez V., Martinez-Gonzalez P., Garcia-Rodriguez J., A survey on deep learning techniques for image and video semantic segmentation, Appl. Soft Comput. 70 (2018) 41–65.
[6]
K. He, G. Gkioxari, P. Dollár, R. Girshick, Mask r-cnn, in: Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy, 2017, pp. 2961–2969.
[7]
Wang J., Liu J., Kato N., Networking and communications in autonomous driving: A survey, IEEE Commun. Surv. Tutor. 21 (2) (2019) 1243–1274.
[8]
Yurtsever E., Lambert J., Carballo A., Takeda K., A survey of autonomous driving: Common practices and emerging technologies, IEEE Access 8 (2020) 58443–58469.
[9]
Wang M., Deng W., Deep face recognition: A survey, Neurocomputing 429 (2021) 215–244.
[10]
Guo G., Zhang N., A survey on deep learning based face recognition, Comput. Vis. Image Underst. 189 (2019).
Digital Library
[11]
Hirschberg J., Manning C.D., Advances in natural language processing, Science 349 (6245) (2015) 261–266.
[12]
N.C. Camgoz, S. Hadfield, O. Koller, H. Ney, R. Bowden, Neural sign language translation, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, USA, 2018, pp. 7784–7793.
[13]
Jain S., White M., Radivojac P., Estimating the class prior and posterior from noisy positives and unlabeled data, Adv. Neural Inf. Process. Syst. 29 (2016) 2693–2701.
[14]
V.S. Sheng, F. Provost, P.G. Ipeirotis, Get Another Label? Improving Data Quality and Data Mining Using Multiple, Noisy Labelers, in: Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Las Vegas, USA, 2008, pp. 614–622.
[15]
F. Sung, Y. Yang, L. Zhang, T. Xiang, P.H. Torr, T.M. Hospedales, Learning to compare: Relation network for few-shot learning, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, USA, 2018, pp. 1199–1208.
[16]
Hou R., Chang H., Ma B., Shan S., Chen X., Cross attention network for few-shot classification, Adv. Neural Inf. Process. Syst. 32 (2019) 4003–4014.
[17]
O. Vinyals, C. Blundell, T. Lillicrap, D. Wierstra, et al., Matching networks for one shot learning, in: Advances in Neural Information Processing Systems, Barcelona, Spain, 2016, pp. 3630–3638.
[18]
J. Snell, K. Swersky, R. Zemel, Prototypical networks for few-shot learning, in: Advances in Neural Information Processing Systems, Long Beach, USA, 2017, pp. 4077–4087.
[19]
B. Oreshkin, P. Rodríguez López, A. Lacoste, TADAM: task dependent adaptive metric for improved few-shot learning, in: Advances in Neural Information Processing Systems, Montréal, Canada, 2018, pp. 719–729.
[20]
C. Finn, P. Abbeel, S. Levine, Model-agnostic meta-learning for fast adaptation of deep networks, in: Proceedings of International Conference on Machine Learning, Sydney, Australia, 2017, pp. 1126–1135.
[21]
A.A. Rusu, D. Rao, J. Sygnowski, O. Vinyals, R. Pascanu, S. Osindero, R. Hadsell, Meta-learning with latent embedding optimization, in: International Conference on Learning Representations, New Orleans, USA, 2019, pp. 1–17.
[22]
French R.M., Catastrophic forgetting in connectionist networks, Trends Cogn. Sci. 3 (4) (1999) 128–135.
[23]
Li Z., Hoiem D., Learning without forgetting, IEEE Trans. Pattern Anal. Mach. Intell. 40 (12) (2018) 2935–2947.
Digital Library
[24]
F. Zenke, B. Poole, S. Ganguli, Continual Learning Through Synaptic Intelligence, in: Proceedings of the International Conference on Machine Learning, Vol. 70, Sydney, Australia, 2017, pp. 3987–3995.
[25]
A. Rannen, R. Aljundi, M.B. Blaschko, T. Tuytelaars, Encoder Based Lifelong Learning, in: Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy, 2017, pp. 1320–1328.
[26]
A. Mallya, S. Lazebnik, PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, USA, 2018, pp. 7765–7773.
[27]
A. Mallya, D. Davis, S. Lazebnik, Piggyback: Adapting a Single Network to Multiple Tasks by Learning to Mask Weights, in: Proceedings of the European Conference on Computer Vision, ECCV, Munich, Germany, 2018, pp. 67–82.
[28]
D. Isele, A. Cosgun, Selective Experience Replay for Lifelong Learning, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 32, New Orleans, USA, 2018, pp. 3302–3309.
[29]
S.-A. Rebuffi, A. Kolesnikov, G. Sperl, C.H. Lampert, iCaRL: Incremental Classifier and Representation Learning, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, USA, 2017, pp. 2001–2010.
[30]
Lee S.-W., Kim J.-H., Jun J., Ha J.-W., Zhang B.-T., Overcoming catastrophic forgetting by incremental moment matching, Adv. Neural Inf. Process. Syst. 30 (2017) 4652–4662.
[31]
X. Tao, X. Hong, X. Chang, S. Dong, X. Wei, Y. Gong, Few-shot class-incremental learning, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Virtual Event, 2020, pp. 12180–12189.
[32]
K. Zhu, Y. Cao, W. Zhai, J. Cheng, Z.-J. Zha, Self-promoted prototype refinement for few-shot class-incremental learning, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Virtual Event, 2021, pp. 6801–6810.
[33]
C. Zhang, N. Song, G. Lin, Y. Zheng, P. Pan, Y. Xu, Few-shot incremental learning with continually evolved classifiers, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Virtual Event, 2021, pp. 12455–12464.
[34]
M. Hersche, G. Karunaratne, G. Cherubini, L. Benini, A. Sebastian, A. Rahimi, Constrained few-shot class-incremental learning, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, New Orleans, USA, 2022, pp. 9057–9067.
[35]
T.E. Boult, S. Cruz, A.R. Dhamija, M. Gunther, J. Henrydoss, W.J. Scheirer, Learning and the unknown: Surveying steps toward open world recognition, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 33, Honolulu, USA, 2019, pp. 9801–9807.
[36]
Xu Y., Chen L., Duan L., Tsang I.W., Luo J., Open set domain adaptation with soft unknown-class rejection, IEEE Trans. Neural Netw. Learn. Syst. 34 (3) (2023) 1601–1612.
[37]
Huang H.-J., Hsu C.-N., Bayesian classification for data from the same unknown class, IEEE Trans. Syst. Man Cybern. B 32 (2) (2002) 137–145.
[38]
Geng C., Huang S.-j., Chen S., Recent advances in open set recognition: A survey, IEEE Trans. Pattern Anal. Mach. Intell. 43 (10) (2020) 3614–3631.
[39]
A. Bendale, T.E. Boult, Towards open set deep networks, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, USA, 2016, pp. 1563–1572.
[40]
P. Pramuditha, M. Patel Vishal, Deep transfer learning for multiple class novelty detection, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, USA, 2019, pp. 11544–11552.
[41]
M. Masana, I. Ruiz, J. Serrat, J. van de Weijer, A.M. Lopez, Metric learning for novelty and anomaly detection, in: British Machine Vision Conference, Newcastle, UK, 2018, pp. 1–17.
[42]
Mendes Júnior P.R., De Souza R.M., Werneck R.d.O., Stein B.V., Pazinato D.V., de Almeida W.R., Penatti O.A., Torres R.d.S., Rocha A., Nearest neighbors distance ratio open-set classifier, Mach. Learn. 106 (3) (2017) 359–386.
[43]
Yang H.-M., Zhang X.-Y., Yin F., Yang Q., Liu C.-L., Convolutional prototype network for open set recognition, IEEE Trans. Pattern Anal. Mach. Intell. 44 (5) (2020) 2358–2370.
[44]
P. Oza, V.M. Patel, C2ae: Class conditioned auto-encoder for open-set recognition, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, USA, 2019, pp. 2307–2316.
[45]
Nichol A., Schulman J., Reptile: a scalable metalearning algorithm, 2018, pp. 1–15. arXiv preprint arXiv:1803.02999 2.
[46]
Yuwono E.I., Tjondonegoro D., Sorwar G., Alaei A., Scalability of knowledge distillation in incremental deep learning for fast object detection, Appl. Soft Comput. 129 (2022).
[47]
F.M. Castro, M.J. Marín-Jiménez, N. Guil, C. Schmid, K. Alahari, End-to-end incremental learning, in: Proceedings of the European Conference on Computer Vision, ECCV, Munich, Germany, 2018, pp. 233–248.
[48]
S. Hou, X. Pan, C.C. Loy, Z. Wang, D. Lin, Learning a unified classifier incrementally via rebalancing, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, USA, 2019, pp. 831–839.
[49]
Y. Wu, Y. Chen, L. Wang, Y. Ye, Z. Liu, Y. Guo, Y. Fu, Large scale incremental learning, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, USA, 2019, pp. 374–382.
[50]
Z. Chi, L. Gu, H. Liu, Y. Wang, Y. Yu, J. Tang, MetaFSCIL: A Meta-Learning Approach for Few-Shot Class Incremental Learning, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, New Orleans, USA, 2022, pp. 14166–14175.
[51]
D.-W. Zhou, F.-Y. Wang, H.-J. Ye, L. Ma, S. Pu, D.-C. Zhan, Forward compatible few-shot class-incremental learning, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, New Orleans, USA, 2022, pp. 9046–9056.
[52]
Wu M., Pan S., Zhu X., Openwgl: Open-world graph learning, IEEE International Conference on Data Mining, IEEE, Sorrento, Italy, 2020, pp. 681–690.
[53]
Prim R.C., Shortest connection networks and some generalizations, Bell Syst. Tech. J. 36 (6) (1957) 1389–1401.
[54]
W. Wang, M. Zhu, X. Zeng, X. Ye, Y. Sheng, Malware traffic classification using convolutional neural network for representation learning, in: International Conference on Information Networking, Da Nang, Vietnam, 2017, pp. 712–717.
[55]
Garcia S., Grill M., Stiborek J., Zunino A., An empirical comparison of botnet detection methods, Comput. Secur. 45 (2014) 100–123.
Digital Library
[56]
Russakovsky O., Deng J., Su H., Krause J., Satheesh S., Ma S., Huang Z., Karpathy A., Khosla A., Bernstein M., et al., Imagenet large scale visual recognition challenge, Int. J. Comput. Vis. 115 (2015) 211–252.
Digital Library
[57]
S. Ravi, H. Larochelle, Optimization as a model for few-shot learning, in: International Conference on Learning Representations, Toulon, France, 2017, pp. 1–11.
[58]
Ye X., Zhao J., Graph convolutional network with unknown class number, IEEE Trans. Multimed. 25 (2023) 4800–4813.
[59]
K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, USA, 2016, pp. 770–778.
Recommendations
- Dual class representation learning for few-shot image classification
Abstract
Few-shot learning (FSL) models are trained on base classes that have many training examples and evaluated on novel classes that have very few training examples. Since these models cannot be properly fine-tuned on the novel classes ...
Highlights
- Proposes dual class representation learning (DCRL) for few-shot image classification.
Read More
- Graph Few-shot Class-incremental Learning
WSDM '22: Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining
The ability to incrementally learn new classes is vital to all real-world artificial intelligence systems. A large portion of high-impact applications like social media, recommendation systems, E-commerce platforms, etc. can be represented by graph ...
Read More
- Flexible few-shot class-incremental learning with prototype container
Abstract
In the few-shot class-incremental learning, new class samples are utilized to learn the characteristics of new classes, while old class exemplars are used to avoid old knowledge forgetting. The limited number of new class samples is more likely to ...
Read More
Comments
Information & Contributors
Information
Published In
Applied Soft Computing Volume 154, Issue C
Mar 2024
1255 pages
ISSN:1568-4946
Issue’s Table of Contents
Elsevier B.V.
Publisher
Elsevier Science Publishers B. V.
Netherlands
Publication History
Published: 02 July 2024
Author Tags
- Few-shot learning
- Incremental learning
- Open set recognition
Qualifiers
- Research-article
Contributors
Other Metrics
View Article Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
Total Citations
Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Other Metrics
View Author Metrics
Citations
View Options
View options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in
Full Access
Get this Publication
Media
Figures
Other
Tables
