Self-adaptive label filtering learning for unsupervised domain adaptation

doi:10.1007/s11704-022-1283-6

Front. Comput. Sci.

2023, Vol. 17

Issue (1) : 171308 https://doi.org/10.1007/s11704-022-1283-6

LETTER

Self-adaptive label filtering learning for unsupervised domain adaptation

Qing TIAN^1,²(

), Heyang SUN¹, Shun PENG¹, Tinghuai MA^1,²

¹. School of Computer and Software, Nanjing University of Information Science and Technology, Nanjing 210044, China
². Engineering Research Center of Digital Forensics, Ministry of Education, Nanjing University of Information Science and Technology, Nanjing 210044, China

Download: PDF(3924 KB) HTML
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks

Corresponding Author(s): Qing TIAN

Just Accepted Date: 29 October 2021 Issue Date: 01 March 2022

Cite this article:

Qing TIAN,Heyang SUN,Shun PENG, et al. Self-adaptive label filtering learning for unsupervised domain adaptation[J]. Front. Comput. Sci., 2023, 17(1): 171308.

URL:

https://academic.hep.com.cn/fcs/EN/10.1007/s11704-022-1283-6
https://academic.hep.com.cn/fcs/EN/Y2023/V17/I1/171308

Fig.1 Illustration of the proposed framework. The probability that a sample belongs to one class is represented by the area occupied by its corresponding color. The more colors in a sample, the more confusing that sample is

Fig.2 Demonstration of label filtering for the predicted pseudo-labels. (a) the confifident label; (b) the ambiguous label

	PCA	JDA	JGSA	DICD	DGA-DA	SALFL
C $→$ A	36.78	45.28	53.07	51.96	52.15	56.22
C $→$ W	31.98	41.89	48.21	47.68	47.34	60.77
C $→$ D	37.54	45.42	48.60	46.21	45.84	59.05
A $→$ C	34.82	39.26	41.66	41.66	41.36	45.95
A $→$ W	35.93	37.88	44.91	38.49	38.38	50.53
A $→$ D	27.52	39.04	45.15	38.65	38.34	48.34
W $→$ C	26.34	31.65	33.47	33.68	33.25	37.03
W $→$ A	31.44	32.73	40.87	41.20	41.56	42.33
W $→$ D	77.87	89.67	88.69	91.17	90.04	93.79
D $→$ C	29.52	30.63	30.50	34.08	33.60	33.67
D $→$ A	31.69	33.27	38.73	33.87	33.56	37.35
D $→$ W	75.80	89.59	93.74	93.76	93.26	94.14
Average	39.77	46.36	50.63	49.37	49.06	54.93

Tab.1 Recognition accuracy (%) on Office-10 + Caltech-10

1	S Wold , K Esbensen , P Geladi . Principal component analysis. Chemometrics and Intelligent Laboratory Systems, 1987, 2( 1−3): 37– 52
2	M Long, G Ding, J Wang, J Sun, Y Guo, P S Yu. Transfer sparse coding for robust image representation. In: Proceedings of 2013 IEEE Conference on Computer Vision and Pattern Recognition. 2013, 407– 414
3	J Zhang, W Li, P Ogunbona. Joint geometrical and statistical alignment for visual domain adaptation. In: Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. 2017, 5150– 5158
4	S Li , S Song , G Huang , Z Ding , C Wu . Domain invariant and class discriminative feature learning for visual domain adaptation. IEEE Transactions on Image Processing, 2018, 27( 9): 4260– 4273
5	L Luo , L Chen , S Hu , Y Lu , X Wang . Discriminative and geometry-aware unsupervised domain adaptation. IEEE Transactions on Cybernetics, 2020, 50( 9): 3914– 3927

[1]		Download
[2]		Download

Viewed

Full text

Abstract

Cited

Shared

Discussed