Research Article
Classification of Long-Tailed Data Based on Bilateral-Branch Generative Network with Time-Supervised Strategy
Algorithm 2
Data generation algorithm.
| | Input: An unbalanced data branch . A resampled data branch . A network f. A pre-trained generative network G. | | | Output: A augmented balanced data branch O | | (1) | | | (2) | for k = in do | | (3) | | | (4) | for i = 1 to do | | (5) | | | (6) | A random sample of class in | | (7) | Add some noise to the | | (8) | for t = 1 to L do | | (9) | | | (10) | | | (11) | | | (12) | | | (13) | end for | | (14) | | | (15) | If or P = 1 then | | (16) | A random sample of class in | | (17) | end if | | (18) | | | (19) | end for | | (20) | end for |
|