MentorNet (Inception-ResNet-v2)

Reported on 2 benchmarks across 1 task · 1 paper · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision2 results

Image Classificationonmini WebVision 1.0
ImageNet Top-1 Accuracy· 2017-12-14
63.8
best: 82.56 (LRA-diffusion (CLIP ViT))
SOTA
MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels arXiv:1712.05055
Image Classificationonmini WebVision 1.0
ImageNet Top-5 Accuracy· 2017-12-14
85.8
best: 97.24 (RTE (Inception-ResNet-v2))
SOTA
MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels arXiv:1712.05055