Improving Image Recognition by Retrieving from Web-Scale Image-Text Data
Open paper
Benchmark
Model
Rank
Results
image-classification-on-webvision-1000
MAM (ViT-B/16)
–
Top-1 Accuracy: 83.6
long-tail-learning-on-imagenet-lt
MAM (ViT-B/16)
–
Top-1 Accuracy: 82.3
long-tail-learning-on-places-lt
MAM (ViT-B/16)
–
Top-1 Accuracy: 51.4
Rank counts only results with a code link.