Page 102 - 《软件学报》2024年第4期

1680 软件学报 2024 年第 35 卷第 4 期

[14] Bendale A, Boult TE. Towards open set deep networks. In: Proc. of the 2016 IEEE/CVF Conf. on Computer Vision and Pattern
Recognition (CVPR). 2016. 1563−1572. [doi: 10.1109/CVPR.2016.173]
[15] Zhou DW, Ye HJ, Zhan DC. Learning placeholders for open-set recognition. In: Proc. of the 2021 IEEE/CVF Conf. on Computer
Vision and Pattern Recognition (CVPR). 2021. 4401−4410. [doi: 10.1109/CVPR46437.2021.00438]
[16] Chen G, Peng P, Wang X, et al. Adversarial reciprocal points learning for open set recognition. IEEE Trans. on Pattern Analysis
and Machine Intelligence, 2022, 44(11): 8065−8081. [doi: 10.1109/TPAMI.2021.3106743]
[17] Sun X, Yang Z, Zhang C, et al. Conditional Gaussian distribution learning for open set recognition. In: Proc. of the 2020
IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR). 2020. 13480−13489. [doi: 10.1109/CVPR42600.2020.
01349]
[18] Geng C, Chen S. Collective decision for open set recognition. IEEE Trans. on Knowledge and Data Engineering, 2020, 34(1):
192−204. [doi: 10.1109/TKDE.2020.2978199]
[19] Shao JJ, Guo LZ, Yang XW, et al. LOG: Active model adaptation for label-efficient ood generalization. In: Advances in Neural
Information Processing Systems. 2022.
[20] Guo LZ, Zhou Z, Li YF. RECORD: Resource constrained semi-supervised learning under distribution shift. In: Proc. of the 26th
ACM SIGKDD Int’l Conf. on Knowledge Discovery and Data Mining. 2020. 1636−1644. [doi: 10.1145/3394486.3403214]
[21] Wang D, Shelhamer E, Liu S, et al. Tent: Fully test-time adaptation by entropy minimization. In: Proc. of the 8th Int’l Conf. on
Learning Representations. 2020.
[22] Niu S, Wu J, Zhang Y, et al. Efficient test-time model adaptation without forgetting. In: Proc. of the 39th Int’l Conf. on Machine
Learning. 2022. 16888−16905.
[23] Bartler A, Bühler A, Wiewel F, et al. MT3: Meta test-time training for self-supervised test-time adaption. In: Proc. of the 25th Int’l
Conf. on Artificial Intelligence and Statistics. 2022. 3080−3090.
[24] Wang Q, Fink O, Van Gool L, et al. Continual test-time domain adaptation. In: Proc. of the 2022 IEEE/CVF Conf. on Computer
Vision and Pattern Recognition (CVPR). 2022. 7191−7201. [doi: 10.1109/CVPR52688.2022.00706]
[25] Boudiaf M, Mueller R, Ayed IB, et al. Parameter-free online test-time adaptation. In: Proc. of the 2022 IEEE/CVF Conf. on
Computer Vision and Pattern Recognition (CVPR). 2022. 8334−8343. [doi: 10.1109/CVPR52688.2022.00816]
[26] Niu S, Wu J, Zhang Y, et al. Towards stable test-time adaptation in dynamic wild world. In: Proc. of the 11th Int’l Conf. on
Learning Representations. 2023.
[27] Gong T, Jeong J, Kim T, et al. Robust continual test-time adaptation: instance-aware bn and prediction-balanced memory. In:
Advances in Neural Information Processing Systems. 2022.
[28] Scheirer WJ, De Rezende Rocha A, Sapkota A, et al. Toward open set recognition. IEEE Trans. on Pattern Analysis and Machine
Intelligence, 2012, 35(7): 1757−1772. [doi: 10.1109/TPAMI.2012.256]
[29] Jain LP, Scheirer WJ, Boult TE. Multi-class open set recognition using probability of inclusion. In: Proc. of the European Conf. on
Computer Vision (ECCV). 2014. 393−409. [doi: 10.1007/978-3-319-10578-9\_26]
[30] Ge Z, Demyanov S, Chen Z, et al. Generative openmax for multi-class open set classification. In: Proc. of the British Machine
Vision Conf. 2017.
[31] Oza P, Patel VM. C2ae: Class conditioned auto-encoder for open-set recognition. In: Proc. of the 2019 IEEE/CVF Conf. on
Computer Vision and Pattern Recognition (CVPR). 2019. 2307−2316. [doi: 10.1109/CVPR.2019.00241]
[32] Shao JJ, Yang XW, Guo LZ. Open-set learning under covariate shift. Machine Learning, 2022. [doi: 10.1007/s10994-022-06237-1]
[33] Sun Y, Wang X, Liu Z, et al. Test-time training with self-supervision for generalization under distribution shifts. In: Proc. of the
37th Int’l Conf. on Machine Learning. 2020. 9229−9248.
[34] Liu Y, Kothari P, Van Delft B, et al. TTT++: When does self-supervised test-time training fail or thrive? In: Advances in Neural
Information Processing Systems. 2021. 21808−21820.
[35] Schneider S, Rusak E, Eck L, et al. Improving robustness against common corruptions by covariate shift adaptation. In: Advances
in Neural Information Processing Systems. 2020. 11539−11551.
[36] Ioffe S, Szegedy C. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In: Proc. of the
32nd Int’l Conf. on Machine Learning. 2015. 448−456.