Long Tail Learning On Imagenet Lt
Metrics
Top-1 Accuracy
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | Top-1 Accuracy |
|---|---|
| batchformer-learning-to-explore-sample | 55.7 |
| feature-space-augmentation-for-long-tailed | 35.3 |
| balanced-meta-softmax-for-long-tailed-visual | 41.8 |
| vl-ltr-learning-class-wise-visual-linguistic | 77.2 |
| adaptive-parametric-activation | 57.9 |
| deit-lt-distillation-strikes-back-for-vision | 59.1 |
| probabilistic-contrastive-learning-for-long | 58.0 |
| probabilistic-contrastive-learning-for-long | 60.2 |
| rethinking-the-value-of-labels-for-improving | 51.3 |
| exploring-balanced-feature-spaces-for | 51.5 |
| a-simple-long-tailed-recognition-baseline-via | 70.5 |
| batchformer-learning-to-explore-sample | 57.4 |
| nested-collaborative-learning-for-long-tailed | 57.4 |
| pure-noise-to-the-rescue-of-insufficient-data | 55.1 |
| targeted-supervised-contrastive-learning-for | 52.4 |
| long-tail-learning-with-attributes | 42.0 |
| long-tailed-recognition-by-routing-diverse-1 | 56.4 |
| distributional-robustness-loss-for-long-tail | 53.5 |
| escaping-saddle-points-for-effective | 53.1 |
| parameter-efficient-long-tailed-recognition | 78.3 |
| difficulty-net-learning-to-predict-difficulty | 54.0 |
| a-continual-development-methodology-for-large | 82.5 |
| improving-calibration-for-long-tailed-1 | 52.7 |
| class-balanced-distillation-for-long-tailed | 57.7 |
| adaptive-parametric-activation | 59.1 |
| mdcs-more-diverse-experts-with-consistency | 61.8 |
| difficulty-net-learning-to-predict-difficulty | 44.6 |
| test-agnostic-long-tailed-recognition-by-test | 61.4 |
| rsg-a-simple-but-effective-module-for | 51.8 |
| difficulty-net-learning-to-predict-difficulty | 57.4 |
| metasaug-meta-semantic-augmentation-for-long | 47.39 |
| a-simple-long-tailed-recognition-baseline-via | 75.7 |
| reslt-residual-learning-for-long-tailed | 52.9 |
| decoupling-representation-and-classifier-for | 41.4 |
| test-agnostic-long-tailed-recognition-by-test | 58.8 |
| large-scale-long-tailed-recognition-in-an | 35.6 |
| metasaug-meta-semantic-augmentation-for-long | 50.03 |
| long-tailed-classification-by-keeping-the-1 | 51.8 |
| the-majority-can-help-the-minority-context | 58.0 |
| long-tailed-recognition-using-class-balanced | 39.2 |
| vl-ltr-learning-class-wise-visual-linguistic | 70.1 |
| improving-image-recognition-by-retrieving | 82.3 |
| class-balanced-distillation-for-long-tailed | 55.6 |
| inflated-episodic-memory-with-region-self | 43.2 |
| parametric-contrastive-learning | 58.2 |
| long-tailed-recognition-by-mutual-information | 58.8 |
| global-and-local-mixture-consistency-1 | 56.3 |
| learning-from-multiple-experts-self-paced | 38.8 |
| nested-collaborative-learning-for-long-tailed | 58.4 |
| a-simple-long-tailed-recognition-baseline-via | 76.5 |
| long-tailed-recognition-via-weight-balancing | 53.9 |
| a-simple-long-tailed-recognition-baseline-via | 67.2 |
| generalized-parametric-contrastive-learning | 63.2 |
| harnessing-hierarchical-label-distribution | 58.61 |
| reslt-residual-learning-for-long-tailed | 55.1 |
| parametric-contrastive-learning | 60.0 |
| distilling-virtual-examples-for-long-tailed | 53.1 |
| rethinking-class-balanced-methods-for-long | 29.9 |
| long-tail-learning-via-logit-adjustment | 51.3 |
| reslt-residual-learning-for-long-tailed | 57.6 |
| blt-balancing-long-tailed-datasets-with | 38.0 |
| balanced-contrastive-learning-for-long-tailed-1 | 57.1 |
| long-tailed-recognition-by-routing-diverse-1 | 54.9 |
| distribution-alignment-a-unified-framework | 53.4 |
| blt-balancing-long-tailed-datasets-with | 44.7 |
| disentangling-label-distribution-for-long | 53.0 |
| parameter-efficient-long-tailed-recognition | 82.9 |
| class-wise-difficulty-balanced-loss-for | 38.5 |
| distilling-virtual-examples-for-long-tailed | 57.12 |