Discriminative Unsupervised Feature Learning with Convolutional Neural Networks
Reported on 2 benchmarks across 1 task
Note: results are matched by exact model name. Different papers may use the same name for different model variants.
Computer Vision2 results
- Percentage correct82best: 99.5 (ViT-H/14)
- Percentage correct72.8best: 99.64 (µ2Net+ (ViT-L/16))