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-18)

OpenLDN (ResNet-18)

Reported on 24 benchmarks across 2 tasks · 1 paper · 14 SOTA

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

Computer Vision24 results

Image ClassificationonCIFAR-100
All accuracy (50% Labeled)· 2022-07-05
60.1
SOTA
OpenLDN: Learning to Discover Novel Classes for Open-World Semi-Supervised Learning arXiv:2207.02261
Image ClassificationonCIFAR-100
Novel accuracy (50% Labeled)· 2022-07-05
46.8
SOTA
OpenLDN: Learning to Discover Novel Classes for Open-World Semi-Supervised Learning arXiv:2207.02261
Image ClassificationonCIFAR-100
Seen accuracy (50% Labeled)· 2022-07-05
73.5
SOTA
OpenLDN: Learning to Discover Novel Classes for Open-World Semi-Supervised Learning arXiv:2207.02261
Image ClassificationonCIFAR-10
All accuracy (10% Labeled)· 2022-07-05
92.8
SOTA
OpenLDN: Learning to Discover Novel Classes for Open-World Semi-Supervised Learning arXiv:2207.02261
Image ClassificationonCIFAR-10
All accuracy (50% Labeled)· 2022-07-05
95.4
best: 97 (SimGCD (ViT-B-16))
SOTA
OpenLDN: Learning to Discover Novel Classes for Open-World Semi-Supervised Learning arXiv:2207.02261
Image ClassificationonCIFAR-10
Novel accuracy (10% Labeled)· 2022-07-05
93.2
SOTA
OpenLDN: Learning to Discover Novel Classes for Open-World Semi-Supervised Learning arXiv:2207.02261
Image ClassificationonCIFAR-10
Novel accuracy (50% Labeled)· 2022-07-05
95.1
best: 98.5 (SimGCD (ViT-B-16))
SOTA
OpenLDN: Learning to Discover Novel Classes for Open-World Semi-Supervised Learning arXiv:2207.02261
Semi-Supervised Image ClassificationonCIFAR-100
All accuracy (50% Labeled)· 2022-07-05
60.1
SOTA
OpenLDN: Learning to Discover Novel Classes for Open-World Semi-Supervised Learning arXiv:2207.02261
Semi-Supervised Image ClassificationonCIFAR-100
Novel accuracy (50% Labeled)· 2022-07-05
46.8
SOTA
OpenLDN: Learning to Discover Novel Classes for Open-World Semi-Supervised Learning arXiv:2207.02261
Semi-Supervised Image ClassificationonCIFAR-100
Seen accuracy (50% Labeled)· 2022-07-05
73.5
SOTA
OpenLDN: Learning to Discover Novel Classes for Open-World Semi-Supervised Learning arXiv:2207.02261
Semi-Supervised Image ClassificationonCIFAR-10
All accuracy (10% Labeled)· 2022-07-05
92.8
SOTA
OpenLDN: Learning to Discover Novel Classes for Open-World Semi-Supervised Learning arXiv:2207.02261
Semi-Supervised Image ClassificationonCIFAR-10
All accuracy (50% Labeled)· 2022-07-05
95.4
best: 97 (SimGCD (ViT-B-16))
SOTA
OpenLDN: Learning to Discover Novel Classes for Open-World Semi-Supervised Learning arXiv:2207.02261
Semi-Supervised Image ClassificationonCIFAR-10
Novel accuracy (10% Labeled)· 2022-07-05
93.2
SOTA
OpenLDN: Learning to Discover Novel Classes for Open-World Semi-Supervised Learning arXiv:2207.02261
Semi-Supervised Image ClassificationonCIFAR-10
Novel accuracy (50% Labeled)· 2022-07-05
95.1
best: 98.5 (SimGCD (ViT-B-16))
SOTA
OpenLDN: Learning to Discover Novel Classes for Open-World Semi-Supervised Learning arXiv:2207.02261
Image ClassificationonCIFAR-100
All accuracy (10% Labeled)· 2022-07-05
47.7
best: 60.3 (TRSSL (ResNet-18))
OpenLDN: Learning to Discover Novel Classes for Open-World Semi-Supervised Learning arXiv:2207.02261
Image ClassificationonCIFAR-100
Novel accuracy (10% Labeled)· 2022-07-05
40
best: 52.1 (TRSSL (ResNet-18))
OpenLDN: Learning to Discover Novel Classes for Open-World Semi-Supervised Learning arXiv:2207.02261
Image ClassificationonCIFAR-100
Seen accuracy (10% Labeled)· 2022-07-05
55
best: 68.5 (TRSSL (ResNet-18))
OpenLDN: Learning to Discover Novel Classes for Open-World Semi-Supervised Learning arXiv:2207.02261
Image ClassificationonCIFAR-10
Seen accuracy (10% Labeled)· 2022-07-05
92.4
best: 94.9 (TRSSL (ResNet-18))
OpenLDN: Learning to Discover Novel Classes for Open-World Semi-Supervised Learning arXiv:2207.02261
Image ClassificationonCIFAR-10
Seen accuracy (50% Labeled)· 2022-07-05
95.7
best: 97.9 (GCD (ViT-B-16))
OpenLDN: Learning to Discover Novel Classes for Open-World Semi-Supervised Learning arXiv:2207.02261
Semi-Supervised Image ClassificationonCIFAR-100
All accuracy (10% Labeled)· 2022-07-05
47.7
best: 60.3 (TRSSL (ResNet-18))
OpenLDN: Learning to Discover Novel Classes for Open-World Semi-Supervised Learning arXiv:2207.02261
Semi-Supervised Image ClassificationonCIFAR-100
Novel accuracy (10% Labeled)· 2022-07-05
40
best: 52.1 (TRSSL (ResNet-18))
OpenLDN: Learning to Discover Novel Classes for Open-World Semi-Supervised Learning arXiv:2207.02261
Semi-Supervised Image ClassificationonCIFAR-100
Seen accuracy (10% Labeled)· 2022-07-05
55
best: 68.5 (TRSSL (ResNet-18))
OpenLDN: Learning to Discover Novel Classes for Open-World Semi-Supervised Learning arXiv:2207.02261
Semi-Supervised Image ClassificationonCIFAR-10
Seen accuracy (10% Labeled)· 2022-07-05
92.4
best: 94.9 (TRSSL (ResNet-18))
OpenLDN: Learning to Discover Novel Classes for Open-World Semi-Supervised Learning arXiv:2207.02261
Semi-Supervised Image ClassificationonCIFAR-10
Seen accuracy (50% Labeled)· 2022-07-05
95.7
best: 97.9 (GCD (ViT-B-16))
OpenLDN: Learning to Discover Novel Classes for Open-World Semi-Supervised Learning arXiv:2207.02261