FG-RAT GAN, a RAT GAN enhanced with an auxiliary classifier and contrastive learning over cross-batch memory, reports lower FID than its backbone on two fine-grained datasets.
In: Proceedings of the 27th International Conference on Neural Information Processing Systems (NIPS’14), pp
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Fine-grained Text to Image Synthesis
FG-RAT GAN, a RAT GAN enhanced with an auxiliary classifier and contrastive learning over cross-batch memory, reports lower FID than its backbone on two fine-grained datasets.