RetFormer: Multimodal Retrieval for Enhancing Image Recognition
Open paper
Benchmark
Model
Rank
Results
long-tail-learning-on-imagenet-lt
RetFormer (ViT-B/16) (extra data)
–
Top-1 Accuracy: 81.9
long-tail-learning-on-places-lt
RetFormer (ViT-B/16) (extra data)
–
Top-1 Accuracy: 52.3
Rank counts only results with a code link.