SGGAN combines self-growing network training, high-confidence pseudo-labeling, and MMD feature matching in a GAN, achieving semi-supervised image recognition accuracy close to supervised methods with only 4% labels.
Describing people: A poselet-based approach to attribute classification
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Semi-Supervised Self-Growing Generative Adversarial Networks for Image Recognition
SGGAN combines self-growing network training, high-confidence pseudo-labeling, and MMD feature matching in a GAN, achieving semi-supervised image recognition accuracy close to supervised methods with only 4% labels.