Long Tail Learning On Cifar 100 Lt R 100
評価指標
Error Rate
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
比較表
| モデル名 | Error Rate |
|---|---|
| do-deep-networks-transfer-invariances-across-1 | 55.65 |
| nested-collaborative-learning-for-long-tailed | 46.7 |
| a-simple-episodic-linear-probe-improves | 57.6 |
| feature-balanced-loss-for-long-tailed-visual-1 | 54.78 |
| revisiting-long-tailed-image-classification | 62.75 |
| the-majority-can-help-the-minority-context | 52.8 |
| balanced-contrastive-learning-for-long-tailed-1 | 46.1 |
| long-tailed-recognition-via-weight-balancing | 46.45 |
| feature-generation-for-long-tail | 53.41 |
| memory-based-jitter-improving-visual | 54.2 |
| escaping-saddle-points-for-effective | 47.0 |
| curvature-balanced-feature-manifold-learning | 49.3 |
| global-and-local-mixture-consistency-1 | 41.59 |
| rsg-a-simple-but-effective-module-for | 55.5 |
| optimal-transport-for-long-tailed-recognition | 53.90 |
| the-majority-can-help-the-minority-context | 58.9 |
| escaping-saddle-points-for-effective | 40.99 |
| escaping-saddle-points-for-effective | 53.4 |
| test-agnostic-long-tailed-recognition-by-test | 50.2 |
| long-tailed-recognition-by-routing-diverse-1 | 52 |
| contrastive-learning-based-hybrid-networks | 55.03 |
| harnessing-hierarchical-label-distribution | 51.62 |
| long-tailed-classification-with-gradual | 48.3 |
| metasaug-meta-semantic-augmentation-for-long | 51.99 |
| learning-prototype-classifiers-for-long | 46.59 |
| weight-guided-class-complementing-for-long | 56.4 |
| learning-imbalanced-datasets-with-label | 57.96 |
| long-tailed-visual-recognition-via-gaussian-1 | 51.29 |
| long-tail-learning-with-attributes | 56.50 |
| parameter-efficient-long-tailed-recognition | 10.9 |
| influence-balanced-loss-for-imbalanced-visual-1 | 61.52 |
| a-simple-long-tailed-recognition-baseline-via | 22.2 |
| difficulty-net-learning-to-predict-difficulty | 47.04 |
| a-unified-generalization-analysis-of-re | 46.95 |
| the-majority-can-help-the-minority-context | 53.4 |
| posterior-re-calibration-for-imbalanced | 56.9 |
| batchformer-learning-to-explore-sample | 47.6 |
| enhanced-long-tailed-recognition-with | - |
| targeted-supervised-contrastive-learning-for | 56.2 |
| long-tailed-recognition-by-routing-diverse-1 | 50.9 |
| class-balanced-loss-based-on-effective-number | 61.68 |
| mdcs-more-diverse-experts-with-consistency | 43.9 |
| visual-prompt-tuning | 19 |
| distributional-robustness-loss-for-long-tail | 52.67 |
| pure-noise-to-the-rescue-of-insufficient-data | 45.8 |
| weight-guided-class-complementing-for-long | 44.9 |
| rethinking-the-value-of-labels-for-improving | 56.57 |
| trustworthy-long-tailed-classification | 50.2 |
| towards-calibrated-model-for-long-tailed | 53.59 |
| the-majority-can-help-the-minority-context | 50 |
| class-wise-difficulty-balanced-loss-for | 57.43 |
| self-supervision-to-distillation-for-long | 54.00 |
| do-we-really-need-a-learnable-classifier-at | 54.7 |
| curvature-balanced-feature-manifold-learning | 59.5 |
| batchformer-learning-to-explore-sample | 48.3 |
| ace-ally-complementary-experts-for-solving | 50.4 |
| parametric-contrastive-learning | 49.10 |
| sure-survey-recipes-for-building-reliable-and | 43.66 |
| parameter-efficient-long-tailed-recognition | 18.3 |
| disentangling-label-distribution-for-long | 54.6 |
| deit-lt-distillation-strikes-back-for-vision | 44.4 |
| towards-calibrated-model-for-long-tailed | 54.55 |
| improving-calibration-for-long-tailed-1 | 53 |
| lpt-long-tailed-prompt-tuning-for-image | 10.9 |
| global-and-local-mixture-consistency-1 | 42.01 |
| long-tailed-recognition-by-mutual-information | 46.0 |