Few Shot Image Classification On Mini 2
評価指標
Accuracy
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 | Accuracy |
|---|---|
| self-supervision-can-be-a-good-few-shot | 65.55 |
| transductive-few-shot-learning-with-meta | 78.55 |
| task-augmentation-by-rotating-for-meta | 65.95 |
| enhancing-few-shot-image-classification | 66.57 |
| simpleshot-revisiting-nearest-neighbor | 64.29 |
| transductive-information-maximization-for-few | 77.80 |
| class-aware-patch-embedding-adaptation-for | 71.97 |
| transductive-decoupled-variational-inference | 86.11 |
| improving-few-shot-visual-classification-with | 55.6 |
| squeezing-backbone-feature-distributions-to | 68.43 |
| sparse-spatial-transformers-for-few-shot | 67.25 |
| task-augmentation-by-rotating-for-meta | 65.38 |
| uncertainty-in-model-agnostic-meta-learning | 51.54 |
| exploring-complementary-strengths-of | 67.28 |
| multi-task-meta-learning-modification-with | 61.94 |
| revisiting-local-descriptor-based-image-to | 51.24 |
| easy-ensemble-augmented-shot-y-shaped | 84.04 |
| learning-embedding-adaptation-for-few-shot | 61.72 |
| on-first-order-meta-learning-algorithms | 49.97 |
| rapid-adaptation-with-conditionally-shifted | 56.88 |
| the-self-optimal-transport-feature-transform | 85.59 |
| tadam-task-dependent-adaptive-metric-for | 58.5 |
| match-them-up-visually-explainable-few-shot | 55.03 |
| how-to-train-your-maml | 52.40 |
| boosting-few-shot-learning-with-adaptive | 67.10 |
| matching-networks-for-one-shot-learning | 46.6 |
| instance-credibility-inference-for-few-shot | 69.66 |
| complementing-representation-deficiency-in | 62.53 |
| improved-few-shot-visual-classification | 77.4 |
| region-comparison-network-for-interpretable | 53.57 |
| sgva-clip-semantic-guided-visual-adapting-of | 97.95 |
| embedding-propagation-smoother-manifold-for | 77.27 |
| diffkendall-a-novel-approach-for-few-shot | 65.56 |
| squeezing-backbone-feature-distributions-to | 85.54 |
| multi-scale-adaptive-task-attention-network | 53.63 |
| geometric-mean-improves-loss-for-few-shot | 65.51 |
| self-supervised-knowledge-distillation-for | 67.04 |
| leveraging-the-feature-distribution-in | 82.92 |
| rethinking-generalization-in-few-shot-1 | 72.40 |
| improved-few-shot-visual-classification | 53.2 |
| meta-learning-with-differentiable-convex | 64.09 |
| hyperbolic-image-embeddings | 51.57 |
| charting-the-right-manifold-manifold-mixup | 64.93 |
| fast-and-generalized-adaptation-for-few-shot | 62.21 |
| deep-comparison-relation-columns-for-few-shot | 62.88 |
| rectifying-the-shortcut-learning-of | 69.28 |
| pushing-the-limits-of-simple-pipelines-for | 95.3 |
| unsupervised-embedding-adaptation-via-early | 76.84 |
| prototypical-networks-for-few-shot-learning | 49.42 |
| learning-to-learn-by-self-critique | 62.86 |
| region-comparison-network-for-interpretable | 57.40 |
| laplacian-regularized-few-shot-learning | 75.57 |
| few-shot-image-recognition-by-predicting | 59.60 |
| open-set-likelihood-maximization-for-few-shot | 71.73 |
| joint-distribution-matters-deep-brownian | 67.83 |
| prototype-completion-for-few-shot-learning | 79.01 |
| meta-learning-with-a-geometry-adaptive | 54.86 |
| delta-encoder-an-effective-sample-synthesis | 59.9 |
| gradient-based-meta-learning-with-learned | 51.7 |
| shallow-bayesian-meta-learning-for-real-world | 67.83 |
| learning-to-compare-relation-network-for-few | 50.4 |
| match-them-up-visually-explainable-few-shot | 56.12 |
| deep-kernel-transfer-in-gaussian-processes | 62.96 |
| 190600562 | 70.1 |
| relational-embedding-for-few-shot | 67.60 |
| unsupervised-embedding-adaptation-via-early | 73.98 |
| few-shot-learning-as-domain-adaptation | 71.88 |
| the-balanced-pairwise-affinities-feature | 85.59 |
| adaptive-dimension-reduction-and-variational | 84.80 |
| meta-curvature | 55.73 |
| simple-semantic-aided-few-shot-learning | 78.94 |
| attribute-surrogates-learning-and-spectral | 74.74 |
| mergednet-a-simple-approach-for-one-shot | 68.05 |
| rich-semantics-improve-few-shot-learning | 65.33 |
| meta-transfer-learning-for-few-shot-learning | 61.2 |
| meta-learning-with-a-geometry-adaptive | 53.52 |
| easy-ensemble-augmented-shot-y-shaped | 70.63 |
| constellation-nets-for-few-shot-learning | 64.89 |
| bridging-multi-task-learning-and-meta | 59.84 |
| context-aware-meta-learning | 96.2 |
| empirical-bayes-transductive-meta-learning-1 | 70.0 |
| dynamic-few-shot-visual-learning-without | 56.20 |
| easy-ensemble-augmented-shot-y-shaped | 82.31 |
| improving-few-shot-visual-classification-with | 79.9 |
| easy-ensemble-augmented-shot-y-shaped | 71.75 |
| pac-bayesian-meta-learning-with-implicit | 52.11 |
| model-agnostic-meta-learning-for-fast | 48.7 |
| joint-distribution-matters-deep-brownian | 67.34 |
| meta-learning-with-implicit-gradients | 49.30 |
| few-shot-learning-by-integrating-spatial-and | 84.81 |
| pseudo-shots-few-shot-learning-with-auxiliary | 73.35 |
| 190511641 | 59.14 |
| espt-a-self-supervised-episodic-spatial | 68.36 |
| adaptive-subspaces-for-few-shot-learning | 67.09 |
| adaptive-cross-modal-few-shot-learning | 65.30 |
| metafun-meta-learning-with-iterative | 64.13 |
| sill-net-feature-augmentation-with-separated | 82.99 |
| hierarchically-structured-meta-learning | 50.38 |
| amortized-bayesian-meta-learning | 45.0 |
| vne-an-effective-method-for-improving-deep | 50.95 |
| complementing-representation-deficiency-in | 61.32 |
| self-supervised-learning-for-few-shot-image | 76.82 |
| gpu-based-self-organizing-maps-for-post | 71.5 |
| tapnet-neural-network-augmented-with-task | 61.65 |
| enhancing-prototypical-few-shot-learning-by | 68.01 |