Multimodal Text and Image Classification on Food-101

Metric: Accuracy (%) (higher is better)

LeaderboardDataset

Results

#	Model↕	Accuracy (%)▼	Extra Data	Paper	Date↕	Code
1	Early Fusion (Bert + InceptionV3)	92.5	No	-	-	Code
2	Late Fusion (Bert + InceptionV3)	84.59	No	-	-	Code