Few Shot Image Classification On Mini 3
Métriques
Accuracy
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | Accuracy |
|---|---|
| pseudo-shots-few-shot-learning-with-auxiliary | 82.51 |
| pushing-the-limits-of-simple-pipelines-for | 98.4 |
| easy-ensemble-augmented-shot-y-shaped | 88.57 |
| sill-net-feature-augmentation-with-separated | 89.14 |
| embedding-propagation-smoother-manifold-for | 88.05 |
| adaptive-subspaces-for-few-shot-learning | 81.65 |
| neural-tmdlayer-modeling-instantaneous-flow | 77.78 |
| instance-credibility-inference-for-few-shot | 80.11 |
| meta-learning-with-a-geometry-adaptive | 71.55 |
| simple-semantic-aided-few-shot-learning | 86.49 |
| diffkendall-a-novel-approach-for-few-shot | 80.79 |
| rectifying-the-shortcut-learning-of | 85.16 |
| attribute-surrogates-learning-and-spectral | 89.19 |
| unsupervised-embedding-adaptation-via-early | 84.36 |
| uncertainty-in-model-agnostic-meta-learning | 64.31 |
| model-agnostic-meta-learning-for-fast | 63.1 |
| easy-ensemble-augmented-shot-y-shaped | 86.28 |
| prototype-completion-for-few-shot-learning | 84.18 |
| relational-embedding-for-few-shot | 82.58 |
| laplacian-regularized-few-shot-learning | 84.72 |
| squeezing-backbone-feature-distributions-to | 84.67 |
| self-supervision-can-be-a-good-few-shot | 83.40 |
| context-aware-meta-learning | 98.6 |
| squeezing-backbone-feature-distributions-to | 91.53 |
| on-first-order-meta-learning-algorithms | 65.99 |
| improved-few-shot-visual-classification | 70.8 |
| task-augmentation-by-rotating-for-meta | 81.96 |
| region-comparison-network-for-interpretable | 75.19 |
| rapid-adaptation-with-conditionally-shifted | 71.94 |
| metafun-meta-learning-with-iterative | 80.82 |
| match-them-up-visually-explainable-few-shot | 70.22 |
| meta-learning-with-a-geometry-adaptive | 70.75 |
| tadam-task-dependent-adaptive-metric-for | 76.7 |
| meta-curvature | 70.33 |
| improving-few-shot-visual-classification-with | 91.5 |
| open-set-likelihood-maximization-for-few-shot | 83.4 |
| shallow-bayesian-meta-learning-for-real-world | 84.28 |
| multi-scale-adaptive-task-attention-network | 72.67 |
| improving-few-shot-visual-classification-with | 73.1 |
| empirical-bayes-transductive-meta-learning-1 | 79.2 |
| hypershot-few-shot-learning-by-kernel | 69.62% |
| pac-bayesian-meta-learning-with-implicit | 63.87 |
| adaptive-dimension-reduction-and-variational | 91.65 |
| boosting-few-shot-learning-with-adaptive | 79.54 |
| sparse-spatial-transformers-for-few-shot | 82.75 |
| deep-comparison-relation-columns-for-few-shot | 75.84 |
| constellation-nets-for-few-shot-learning | 79.95 |
| matching-networks-for-one-shot-learning | 60 |
| bridging-multi-task-learning-and-meta | 77.72 |
| transductive-decoupled-variational-inference | 95.95 |
| complementing-representation-deficiency-in | 80.34 |
| 190600562 | 78.7 |
| rethinking-generalization-in-few-shot-1 | 86.38 |
| how-to-train-your-maml | 67.15 |
| simpleshot-revisiting-nearest-neighbor | 81.5 |
| improved-few-shot-visual-classification | 90.3 |
| gpu-based-self-organizing-maps-for-post | 82.2 |
| edge-labeling-graph-neural-network-for-few | 76.37 |
| prototypical-networks-for-few-shot-learning | 68.20 |
| hyperbolic-image-embeddings | 66.27 |
| espt-a-self-supervised-episodic-spatial | 84.11 |
| region-comparison-network-for-interpretable | 71.63 |
| leveraging-the-feature-distribution-in | 88.82 |
| mergednet-a-simple-approach-for-one-shot | 80.40 |
| match-them-up-visually-explainable-few-shot | 71.93 |
| self-supervised-knowledge-distillation-for | 83.54 |
| self-supervised-learning-for-few-shot-image | 90.98 |
| few-shot-learning-as-domain-adaptation | 84.07 |
| geometric-mean-improves-loss-for-few-shot | 81.13 |
| the-self-optimal-transport-feature-transform | 91.34 |
| tapnet-neural-network-augmented-with-task | 76.36 |
| vne-an-effective-method-for-improving-deep | 67.52 |
| easy-ensemble-augmented-shot-y-shaped | 89.14 |
| the-balanced-pairwise-affinities-feature | 91.34 |
| task-augmentation-by-rotating-for-meta | 82.13 |
| sgva-clip-semantic-guided-visual-adapting-of | 98.72 |
| easy-ensemble-augmented-shot-y-shaped | 87.15 |
| embedding-propagation-smoother-manifold-for | 84.34 |
| exploring-complementary-strengths-of | 84.78 |
| few-shot-image-recognition-by-predicting | 73.74 |
| unsupervised-embedding-adaptation-via-early | 82.32 |
| dynamic-few-shot-visual-learning-without | 72.81 |
| learning-embedding-adaptation-for-few-shot | 78.38 |
| 190511641 | 74.63 |
| meta-learning-with-differentiable-convex | 80 |
| enhancing-few-shot-image-classification | 84.42 |
| adaptive-cross-modal-few-shot-learning | 78.10 |
| deep-kernel-transfer-in-gaussian-processes | 64.0 |
| charting-the-right-manifold-manifold-mixup | 83.18 |
| meta-transfer-learning-for-few-shot-learning | 75.5 |
| revisiting-local-descriptor-based-image-to | 71.02 |
| class-aware-patch-embedding-adaptation-for | 87.06 |
| fast-and-generalized-adaptation-for-few-shot | 80.75 |
| learning-to-learn-by-self-critique | 77.64 |
| complementing-representation-deficiency-in | 78.16 |