Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/OpenLDN (ResNet-50)

OpenLDN (ResNet-50)

Reported on 6 benchmarks across 2 tasks · 1 paper · 2 SOTA

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

Computer Vision6 results

Image ClassificationonImageNet-100 (TEMI Split)
All accuracy (50% Labeled)· 2022-07-05
79.1
best: 83.6 (SimGCD (ViT-B-16))
SOTA
OpenLDN: Learning to Discover Novel Classes for Open-World Semi-Supervised Learning arXiv:2207.02261
Semi-Supervised Image ClassificationonImageNet-100 (TEMI Split)
All accuracy (50% Labeled)· 2022-07-05
79.1
best: 83.6 (SimGCD (ViT-B-16))
SOTA
OpenLDN: Learning to Discover Novel Classes for Open-World Semi-Supervised Learning arXiv:2207.02261
Image ClassificationonImageNet-100 (TEMI Split)
Novel accuracy (50% Labeled)· 2022-07-05
68.6
best: 79.1 (SimGCD (ViT-B-16))
OpenLDN: Learning to Discover Novel Classes for Open-World Semi-Supervised Learning arXiv:2207.02261
Image ClassificationonImageNet-100 (TEMI Split)
Seen accuracy (50% Labeled)· 2022-07-05
89.6
best: 92.4 (SimGCD (ViT-B-16))
OpenLDN: Learning to Discover Novel Classes for Open-World Semi-Supervised Learning arXiv:2207.02261
Semi-Supervised Image ClassificationonImageNet-100 (TEMI Split)
Novel accuracy (50% Labeled)· 2022-07-05
68.6
best: 79.1 (SimGCD (ViT-B-16))
OpenLDN: Learning to Discover Novel Classes for Open-World Semi-Supervised Learning arXiv:2207.02261
Semi-Supervised Image ClassificationonImageNet-100 (TEMI Split)
Seen accuracy (50% Labeled)· 2022-07-05
89.6
best: 92.4 (SimGCD (ViT-B-16))
OpenLDN: Learning to Discover Novel Classes for Open-World Semi-Supervised Learning arXiv:2207.02261