Binocular Perception Instance Authentication Learning for Few-Shot Visual Recognition
Source abstract
Abstract
Humans possess unique advantages in dealing with few-shot visual recognition scenarios, inspiring the development of meta-learning methods aimed at emulating these abilities. Current mainstream meta-learning primarily utilizes the monocular vision or the dual asymmetric complementary architectures, collectively referred to as Machine-visual Meta-Learning (MvML). Nevertheless, research has not yet developed an architecture for simulating the human binocular visual system, named Humanoid-visual Meta-Learning (HvML). This paper innovatively proposes an excellent paradigm BPIAL belonging to the HvML: Binocular Perception Instance Authentication Learning, which can alleviate the monocular shallowness and dual-branch processing instability of MvML. Structurally, our BPIAL comprises two interconnected binocular perception and information processing modules: BSEM and IAPM. The former module can simulate binocular visual field extraction, feature extraction and compression, and channel dimension reduction, while IAPM can simulate the logic, reasoning, and judgment processes of the two human visual branches and the brain. We have demonstrated the feasibility and correctness of BPIAL on five benchmarks. Sufficient and comparative experiments with the state-of-the-art methods have proved its superiority and effectiveness.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Domain Adaptation and Few-Shot Learning · Adversarial Robustness in Machine Learning · Human Pose and Action Recognition
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Faculty of Computing, Harbin Institute of Technology, Harbin 150001, China
School of Mechanical Engineering and Automation, Harbin Institute of Technology Shenzhen, Shenzhen 518055, China
Research Institute of Intelligent Control and Systems, Harbin Institute of Technology, Harbin 150001, China
Funding
Key Science & Technology Project of Anhui Province · National Natural Science Foundation of China
References (70)
Show source-provided references
1. Simonyan, K., and Zisserman, A. (2015, January 7–9). Very deep convolutional networks for large-scale image recognition. Proceedings of the International Conference on Learning Representations (ICLR), San Diego, CA, USA.
2. Supervised and unsupervised parallel subspace learning for large-scale image recognition10.1109/TCSVT.2012.2202079 ↗
3. Imagenet large scale visual recognition challenge10.1007/s11263-015-0816-y ↗
4. Multi-scale metric learning for few-shot learning10.1109/TCSVT.2020.2995754 ↗
5. Meta-learning in neural networks: A survey
6. Li, X., Sun, Q., Liu, Y., Zhou, Q., Zheng, S., Chua, T., and Schiele, B. (2019, January 8–14). Learning to self-train for semi-supervised few-shot classification. Proceedings of the 33rd Conference on Neural Information Processing Systems (NeurIPS), Vancouver Convention Centre, Vancouver, BC, Canada.
7. A Survey on Stability of Learning with Limited Labelled Data and its Sensitivity to the Effects of Randomness10.1145/3691339 ↗
8. Ye, H.-J., Hu, H., Zhan, D.C., and Sha, F. (2020, January 14–19). Few-shot learning via embedding adaptation with set-to-set functions. Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.10.1109/CVPR42600.2020.00883 ↗
9. Zhou, Z., Qiu, X., Xie, J., Wu, J., and Zhang, C. (2021, January 10–17). Binocular mutual learning for improving few-shot classification. Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision (ICCV), Montreal, QC, Canada.10.1109/ICCV48922.2021.00829 ↗
10. Liu, Y., Zhang, W., Xiang, C., Zheng, T., and Cai, D. (2022, January 18–24). Learning to affiliate: Mutual centralized learning for few-shot classification. Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.10.1109/CVPR52688.2022.01401 ↗
11. Yang, L., Li, L., Zhang, Z., Zhou, X., Zhou, E., and Liu, Y. (2020, January 14–19). Dpgn: Distribution propagation graph network for few-shot learning. Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.10.1109/CVPR42600.2020.01340 ↗
12. MuL-GRN: Multi-Level Graph Relation Network for Few-Shot Node Classification
13. Lu, Y., Wen, L., Liu, J., Liu, Y., and Tian, X. (2022, January 23–27). Self-supervision can be a good few-shot learner. Proceedings of the 17th European Conference on Computer Vision (ECCV), Tel Aviv, Israel.10.1007/978-3-031-19800-7_43 ↗
14. Lichtenstein, M., Sattigeri, P., Feris, R.S., Giryes, R., and Karlinsky, L. (2020, January 23–28). Tafssl: Task-adaptive feature sub-space learning for few-shot classification. Proceedings of the 16th European Conference on Computer Vision (ECCV), Glasgow, UK.10.1007/978-3-030-58571-6_31 ↗
15. Afrasiyabi, A., Lalonde, J.-F., and Gagné, C. (2021, January 10–17). Mixture-based feature space learning for few-shot image classification. Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision (ICCV), Montreal, QC, Canada.10.1109/ICCV48922.2021.00891 ↗
16. Snell, J., Swersky, K., and Zemel, R.S. (2017, January 4–9). Prototypical networks for few-shot learning. Proceedings of the 31st Annual Conference on Neural Information Processing Systems (NeurIPS), Long Beach, CA, USA.
17. Vinyals, O., Blundell, C., Lillicrap, T.P., Kavukcuoglu, K., and Wierstra, D. (2016, January 5–10). Matching networks for one shot learning. Proceedings of the 30th Annual Conference on Neural Information Processing Systems (NeurIPS), Barcelona, Spain.
18. Sung, F., Yang, Y., Zhang, L., Xiang, T., Torr, P.H.S., and Hospedales, T.M. (2018, January 18–22). Learning to compare: Relation network for few-shot learning. Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.10.1109/CVPR.2018.00131 ↗
19. Hou, R., Chang, H., Ma, B., Shan, S., and Chen, X. (2019, January 8–14). Cross attention network for few-shot classification. Proceedings of the 33rd Conference on Neural Information Processing Systems (NeurIPS), Vancouver, BC, Canada.
20. Finn, C., Abbeel, P., and Levine, S. (2017, January 6–11). Model-agnostic meta-learning for fast adaptation of deep networks. Proceedings of the 34th International Conference on Machine Learning (ICML), Sydney, NSW, Australia.
21. Rusu, A.A., Rao, D., Sygnowski, J., Vinyals, O., Pascanu, R., Osindero, S., and Hadsell, R. (2019, January 6–9). Meta-learning with latent embedding optimization. Proceedings of the 7th International Conference on Learning Representations (ICLR), New Orleans, LA, USA.
22. Lee, K., Maji, S., Ravichandran, A., and Soatto, S. (2019, January 16–20). Meta-learning with differentiable convex optimization. Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.10.1109/CVPR.2019.01091 ↗
23. Oreshkin, B.N., López, P.R., and Lacoste, A. (2018, January 3–8). Tadam: Task dependent adaptive metric for improved few-shot learning. Proceedings of the 32nd Conference on Neural Information Processing Systems (NeurIPS), Montreal, QC, Canada.
24. Qiao, L., Shi, Y., Li, J., Wang, Y., Huang, T., and Tian, Y. (November, January 27). Transductive episodic-wise adaptive metric for few-shot learning. Proceedings of the 17th IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Republic of Korea.
25. Zhang, C., Cai, Y., Lin, G., and Shen, C. (2020, January 14–19). Deepemd: Few-shot image classification with differentiable earth mover’s distance and structured classifiers. Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.10.1109/CVPR42600.2020.01222 ↗
26. Xie, J., Long, F., Lv, J., Wang, Q., and Li, P. (2022, January 18–24). Joint distribution matters: Deep brownian distance covariance for few-shot classification. Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.10.1109/CVPR52688.2022.00781 ↗
27. Revisiting Few-Shot Learning From a Causal Perspective10.1109/TKDE.2024.3397689 ↗
28. Seeing in three dimensions: The neurophysiology of stereopsis10.1016/S1364-6613(99)01443-6 ↗
29. Andrews, T.J. (2001). Binocular rivalry and visual awareness. Neural Correlates of Consciousness: Empirical and Conceptual Questions, MIT Press.
30. Peng, H., Li, B., Xiong, W., Hu, W., and Ji, R. (2014, January 6–12). RGBD Salient Object Detection: A Benchmark and Algorithms. Proceedings of the 13th European Conference on Computer Vision (ECCV), Zurich, Switzerland.10.1007/978-3-319-10578-9_7 ↗
31. Zhu, C., Cai, X., Huang, K., Li, T.H., and Li, G. (2019, January 8–12). PDNet: Prior-Model Guided Depth-Enhanced Network for Salient Object Detection. Proceedings of the 2019 IEEE International Conference on Multimedia and Expo (ICME), Shanghai, China.10.1109/ICME.2019.00042 ↗
32. Three-Stream Attention-Aware Network for RGB-D Salient Object Detection10.1109/TIP.2019.2891104 ↗
33. Chen, Y., Liu, Z., Xu, H., Darrell, T., and Wang, X. (2021, January 11–17). Meta-baseline: Exploring simple meta-learning for few-shot learning. Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision (ICCV), Montreal, QC, Canada.10.1109/ICCV48922.2021.00893 ↗
34. Deepemd: Differentiable earth mover’s distance for few-shot learning
35. Liu, J., Song, L., and Qin, Y. (2018, January 8–14). Prototype rectification for few-shot learning. Proceedings of the 15th European Conference on Computer Vision (ECCV), Munich, Germany.
36. Kang, D., Kwon, H., Min, J., and Cho, M. (2021, January 10–17). Relational embedding for few-shot classification. Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision (ICCV), Montreal, QC, Canada.10.1109/ICCV48922.2021.00870 ↗
37. Fei, N., Lu, Z., Xiang, T., and Huang, S. (2021, January 3–7). Melr: Meta-learning via modeling episode-level relationships for few-shot learning. Proceedings of the 9th International Conference on Learning Representations (ICLR), Vienna, Austria.
38. Task-Oriented Channel Attention for Fine-Grained Few-Shot Classification10.1109/TPAMI.2024.3504537 ↗
39. Huang, K., Geng, J., Jiang, W., Deng, X., and Xu, Z. (2021, January 11–17). Pseudo-loss confidence metric for semi-supervised few-shot learning. Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision (ICCV), Montreal, QC, Canada.10.1109/ICCV48922.2021.00855 ↗
40. Locally-enriched cross-reconstruction for few-shot fine-grained image classification10.1109/TCSVT.2023.3275382 ↗
41. Self-reconstruction network for fine-grained few-shot classification10.1016/j.patcog.2024.110485 ↗
42. Yang, S., Liu, L., and Xu, M. (2021, January 3–7). Free lunch for few-shot learning: Distribution calibration. Proceedings of the 9th International Conference on Learning Representations (ICLR), Vienna, Austria.
43. Wang, Y., Xu, C., Liu, C., Zhang, L., and Fu, Y. (2020, January 14–19). Instance credibility inference for few-shot learning. Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.10.1109/CVPR42600.2020.01285 ↗
44. How to trust unlabeled data? Instance credibility inference for few-shot learning10.1109/TPAMI.2021.3086140 ↗
45. Variational neuron shifting for few-shot image classification across domains10.1109/TMM.2023.3282492 ↗
46. Negatives Make a Positive: An Embarrassingly Simple Approach to Semi-Supervised Few-Shot Learning10.1109/TPAMI.2023.3333528 ↗
47. Medoptnet: Meta-learning framework for few-shot medical image classification10.1109/TCBB.2023.3284846 ↗
48. Wah, C., Branson, S., Welinder, P., Perona, P., and Belongie, S.J. (2026, July 14). The Caltech-Ucsd Birds-200-2011 Dataset, 2011. Available online: https://authors.library.caltech.edu/records/cvm3y-5hh21.
49. Maji, S., Rahtu, E., Kannala, J., Blaschko, M.B., and Vedaldi, A. (2013). Fine-grained visual classification of aircraft. arXiv.
50. Ravi, S., and Larochelle, H. (2017, January 24–26). Optimization as a model for few-shot learning. Proceedings of the 5th International Conference on Learning Representations (ICLR), Toulon, France.
51. Ren, M., Triantafillou, E., Ravi, S., Snell, J., Swersky, K., Tenenbaum, J.B., Larochelle, H., and Zemel, R.S. (May, January 30). Meta-learning for semi-supervised few-shot classification. Proceedings of the 6th International Conference on Learning Representations (ICLR), Vancouver, BC, Canada.
52. Liu, Y., Lee, J., Park, M., Kim, S., Yang, E., Hwang, S.J., and Yang, Y. (2019, January 6–9). Learning to propagate labels: Transductive propagation network for few-shot learning. Proceedings of the 7th International Conference on Learning Representations (ICLR), New Orleans, LA, USA.
53. Tian, Y., Wang, Y., Krishnan, D., Tenenbaum, J.B., and Isola, P. (2020, January 23–28). Rethinking few-shot image classification: A good embedding is all you need?. Proceedings of the 16th European Conference on Computer Vision (ECCV), Glasgow, UK.10.1007/978-3-030-58568-6_16 ↗
54. Baik, S., Choi, J., Kim, H., Cho, D., Min, J., and Lee, K.M. (2021, January 10–17). Meta-learning with task-adaptive loss function for few-shot learning. Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision (ICCV), Montreal, QC, Canada.10.1109/ICCV48922.2021.00933 ↗
55. Wertheimer, D., Tang, L., and Hariharan, B. (2021, January 19–25). Few-shot classification with feature map reconstruction networks. Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Virtual Conference.10.1109/CVPR46437.2021.00792 ↗
56. Few-shot learning meets transformer: Unified query-support transformers for few-shot classification10.1109/TCSVT.2023.3282777 ↗
57. Zhang, M., Zhang, J., Lu, Z., Xiang, T., Ding, M., and Huang, S. (2021, January 3–7). Iept: Instance-level and episode-level pretext tasks for few-shot learning. Proceedings of the 9th International Conference on Learning Representations (ICLR), Virtual Event, Austria.
58. Few-shot classification with Fork Attention Adapter10.1016/j.patcog.2024.110805 ↗
59. Textual enhanced adaptive meta-fusion for few-shot visual recognition10.1109/TMM.2023.3295731 ↗
60. FADS: Fourier-Augmentation Based Data-Shunting for Few-Shot Classification10.1109/TCSVT.2023.3292519 ↗
61. Chen, W.-Y., Liu, Y.-C., Kira, Z., Wang, Y., and Huang, J.-B. (2019, January 6–9). A closer look at few-shot classification. Proceedings of the 7th International Conference on Learning Representations (ICLR), New Orleans, LA, USA.
62. Zhou, F., Wu, B., and Li, Z. (2018). Deep meta-learning: Learning to learn in the concept space. arXiv.
63. Contextualizing Meta-Learning via Learning to Decompose10.1109/TPAMI.2023.3317425 ↗
64. Li, K., Zhang, Y., Li, K., and Fu, Y.R. (2020, January 14–19). Adversarial feature hallucination networks for few-shot learning. Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.10.1109/CVPR42600.2020.01348 ↗
65. Wu, J., Zhang, T., Zhang, Y., and Wu, F. (2021, January 10–17). Task-aware part mining network for few-shot learning. Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision (ICCV), Montreal, QC, Canada.10.1109/ICCV48922.2021.00832 ↗
66. Gidaris, S., Bursuc, A., Komodakis, N., Pérez, P., and Cord, M. (November, January 27). Boosting few-shot visual learning with self-supervision. Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Republic of Korea.10.1109/ICCV.2019.00815 ↗
67. Shen, X., Xiao, Y., Hu, S.X., Sbai, O., and Aubry, M. (2021, January 6–14). Re-ranking for image retrieval and transductive few-shot classification. Proceedings of the 35th Conference on Neural Information Processing Systems (NeurIPS), Virtual Event.
68. Hiller, M., Ma, R., Harandi, M., and Drummond, T. (December, January 28). Rethinking generalization in few-shot classification. Proceedings of the 36th Conference on Neural Information Processing Systems (NeurIPS), New Orleans, LA, USA.
69. Lazarou, M., Avrithis, Y., and Stathaki, T. (2021, January 11–17). Iterative label cleaning for transductive and semi-supervised few-shot learning. Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision (ICCV), Montreal, QC, Canada.10.1109/ICCV48922.2021.00863 ↗
70. Xu, J., Le, H.M., Huang, M., Athar, S., and Samaras, D. (2021, January 11–17). Variational feature disentangling for fine-grained few-shot classification. Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision (ICCV), Montreal, QC, Canada.10.1109/ICCV48922.2021.00869 ↗