Few Shot Image Classification On Cub 200 5 1
평가 지표
Accuracy
평가 결과
이 벤치마크에서 각 모델의 성능 결과
비교 표
| 모델 이름 | Accuracy |
|---|---|
| learning-embedding-adaptation-for-few-shot | 68.65 |
| easy-ensemble-augmented-shot-y-shaped | 90.5 |
| easy-ensemble-augmented-shot-y-shaped | 78.56 |
| transductive-information-maximization-for-few | 82.2% |
| hypershot-few-shot-learning-by-kernel | 66.13 |
| the-balanced-pairwise-affinities-feature | 95.80 |
| revisiting-local-descriptor-based-image-to | 53.15 |
| easy-ensemble-augmented-shot-y-shaped | 90.56 |
| the-self-optimal-transport-feature-transform | 95.80 |
| exploiting-unsupervised-inputs-for-accurate | 88.35% |
| learning-to-compare-relation-network-for-few | 50.44 |
| few-shot-learning-by-integrating-spatial-and | 95.48 |
| context-aware-meta-learning | 95.8 |
| mergednet-a-simple-approach-for-one-shot | 75.34 |
| squeezing-backbone-feature-distributions-to | 94.78 |
| laplacian-regularized-few-shot-learning | 80.96 |
| learning-to-learn-by-self-critique | 67.48 |
| rich-semantics-improve-few-shot-learning | 65.66 |
| charting-the-right-manifold-manifold-mixup | 80.68 |
| learning-to-learn-by-self-critique | 70.46 |
| task-discrepancy-maximization-for-fine-1 | 84.36 |
| negative-margin-matters-understanding-margin | 72.66 |
| transfer-learning-based-few-shot | 91.68 |
| unsupervised-embedding-adaptation-via-early | 82.68 |
| delta-encoder-an-effective-sample-synthesis | 69.8 |
| relational-embedding-for-few-shot | 79.49 |
| hyperbolic-image-embeddings | 60.52 |
| sill-net-feature-augmentation-with-separated | 94.73 |
| espt-a-self-supervised-episodic-spatial | 85.45 |
| variational-transfer-learning-for-fine | 79.12 |
| adaptive-dimension-reduction-and-variational | 90.42 |
| self-supervised-learning-for-few-shot-image | 77.09 |
| instance-credibility-inference-for-few-shot | 89.58 |
| deep-kernel-transfer-in-gaussian-processes | 72.27 |
| easy-ensemble-augmented-shot-y-shaped | 77.97 |
| leveraging-the-feature-distribution-in | 91.55% |