Page 172 - 《软件学报》2026年第4期

王家祺 等: 可解释深度学习的概念建模方法综述 1613

the 2021 Conf. on Empirical Methods in Natural Language Processing. Punta Cana: ACL, 2021. 836–850. [doi: 10.18653/v1/2021.emnlp-
main.64]
[55] Nauta M, van Bree R, Seifert C. Neural prototype trees for interpretable fine-grained image recognition. In: Proc. of the 2021 IEEE/CVF
Conf. on Computer Vision and Pattern Recognition. Nashville: IEEE, 2021. 14928–14938. [doi: 10.1109/CVPR46437.2021.01469]
[56] Hase P, Chen CF, Li O, Rudin C. Interpretable image recognition with hierarchical prototypes. In: Proc. of the 7th AAAI Conf. on Human
Computation and Crowdsourcing. Washington: AAAI, 2019. 32–40. [doi: 10.1609/hcomp.v7i1.5265]
[57] Wang JQ, Liu HF, Wang XY, Jing LP. Interpretable image recognition by constructing transparent embedding space. In: Proc. of the
2021 IEEE/CVF Int’l Conf. on Computer Vision. Montreal: IEEE, 2021. 875–884. [doi: 10.1109/ICCV48922.2021.00093]
[58] Wang JQ, Liu HF, Jing LP. Transparent embedding space for interpretable image recognition. IEEE Trans. on Circuits and Systems for
Video Technology, 2024, 34(5): 3204–3219. [doi: 10.1109/TCSVT.2023.3314769]
[59] Rymarczyk D, Struski Ł, Tabor J, Zieliński B. ProtoPShare: Prototypical parts sharing for similarity discovery in interpretable image
classification. In: Proc. of the 27th ACM SIGKDD Conf. on Knowledge Discovery & Data Mining. ACM, 2021. 1420–1430. [doi: 10.
1145/3447548.3467245]
[60] Xue MQ, Huang QH, Zhang HF, Cheng LC, Song J, Wu MH, Song ML. ProtoPFormer: Concentrating on prototypical parts in vision
Transformers for interpretable image recognition. arXiv:2208.10431, 2022.
[61] Donnelly J, Barnett AJ, Chen CF. Deformable ProtoPNet: An interpretable image classifier using deformable prototypes. In: Proc. of the
2022 IEEE/CVF Conf. on Computer Vision and Pattern Recognition. New Orleans: IEEE, 2022. 10255–10265. [doi: 10.1109/
CVPR52688.2022.01002]
[62] Wang BS, Wang CY, Chiu WC. MCPNet: An interpretable classifier via multi-level concept prototypes. In: Proc. of the 2024 IEEE/CVF
Conf. on Computer Vision and Pattern Recognition. Seattle: IEEE, 2024. 10885–10894. [doi: 10.1109/CVPR52733.2024.01035]
[63] Sawada Y, Nakamura K. Concept bottleneck model with additional unsupervised concepts. IEEE Access, 2022, 10: 41758–41765. [doi:
10.1109/ACCESS.2022.3167702]
[64] Sarkar A, Vijaykeerthy D, Sarkar A, Balasubramanian VN. A framework for learning ante-hoc explainable models via concepts. In: Proc.
of the 2022 IEEE/CVF Conf. on Computer Vision and Pattern Recognition. New Orleans: IEEE, 2022. 10276–10285. [doi: 10.1109/
CVPR52688.2022.01004]
[65] Marconato E, Passerini A, Teso S. GlanceNets: Interpretable, leak-proof concept-based models. In: Proc. of the 36th Int’l Conf. on Neural
Information Processing Systems. New Orleans: Curran Associates Inc., 2022. 21212–21227.
[66] Yang Y, Panagopoulou A, Zhou SH, Jin D, Callison-Burch C, Yatskar M. Language in a bottle: Language model guided concept
bottlenecks for interpretable image classification. In: Proc. of the 2023 IEEE/CVF Conf. on Computer Vision and Pattern Recognition.
Vancouver: IEEE, 2023. 19187–19197. [doi: 10.1109/CVPR52729.2023.01839]
[67] Oikarinen T, Das S, Nguyen LM, Weng TW. Label-free concept bottleneck models. arXiv:2304.06129, 2023.
[68] Wang JQ, Wang PC, Feng Y, Liu HF, Gao C, Jing LP. Align2Concept: Language guided interpretable image recognition by visual
prototype and textual concept alignment. In: Proc. of the 32nd ACM Int’l Conf. on Multimedia. Melbourne: ACM, 2024. 8972–8981.
[doi: 10.1145/3664647.3680707]
[69] Radford A, Kim JW, Hallacy C, Ramesh A, Goh G, Agarwal S, Sastry G, Askell A, Mishkin P, Clark J, Krueger G, Sutskever I. Learning
transferable visual models from natural language supervision. In: Proc. of the 38th Int’l Conf. on Machine Learning. PMLR, 2021.
8748–8763.
[70] Colin J, Fel T, Cadène R, Serre T. What I cannot predict, I do not understand: A human-centered evaluation framework for explainability
methods. In: Proc. of the 36th Int’l Conf. on Neural Information Processing Systems. New Orleans: Curran Associates Inc., 2022.
2832–2845.
[71] Rosch E. Cognitive representations of semantic categories. Journal of Experimental Psychology: General, 1975, 104(3): 192–233. [doi: 10.
1037/0096-3445.104.3.192]
[72] Gärdenfors P. Conceptual Spaces: The Geometry of Thought. Cambridge: MIT Press, 2000.
[73] Wei J, Wang XZ, Schuurmans D, Bosma M, Ichter B, Xia F, Chi EH, Le QV, Zhou D. Chain-of-thought prompting elicits reasoning in
large language models. In: Proc. of the 36th Int’l Conf. on Neural Information Processing Systems. New Orleans: Curran Associates Inc.,
2022. 24824–24837.
[74] Marvin G, Hellen N, Jjingo D, Nakatumba-Nabende J. Prompt engineering in large language models. In: Proc. of the 2024 Int’l Conf. on
Data Intelligence and Cognitive Informatics. Singapore: Springer, 2024. 387–402. [doi: 10.1007/978-981-99-7962-2_30]
[75] Zhao HY, Chen HJ, Yang F, Liu NH, Deng HQ, Cai HY, Wang SQ, Yin DW, Du MN. Explainability for large language models: A
survey. ACM Trans. on Intelligent Systems and Technology, 2024, 15(2): 20. [doi: 10.1145/3639372]