Few Shot Image Classification On Cub 200 5

Accuracy

평가 결과

이 벤치마크에서 각 모델의 성능 결과

비교 표

모델 이름	Accuracy
context-aware-meta-learning	98.7
laplacian-regularized-few-shot-learning	88.68
learning-to-learn-by-self-critique	83.8
charting-the-right-manifold-manifold-mixup	90.85
easy-ensemble-augmented-shot-y-shaped	91.59
revisiting-local-descriptor-based-image-to	81.9
deep-kernel-transfer-in-gaussian-processes	85.64
the-balanced-pairwise-affinities-feature	97.12
hyperbolic-image-embeddings	72.22
instance-credibility-inference-for-few-shot	92.48
easy-ensemble-augmented-shot-y-shaped	93.5
adaptive-dimension-reduction-and-variational	93.50
task-discrepancy-maximization-for-fine-1	93.37
leveraging-the-feature-distribution-in	93.99
transductive-information-maximization-for-few	90.8
sill-net-feature-augmentation-with-separated	96.28
variational-transfer-learning-for-fine	91.48
espt-a-self-supervised-episodic-spatial	94.02
unsupervised-embedding-adaptation-via-early	88.65
transfer-learning-based-few-shot	94.09
hypershot-few-shot-learning-by-kernel	80.07
negative-margin-matters-understanding-margin	89.40
squeezing-backbone-feature-distributions-to	96.43
the-self-optimal-transport-feature-transform	97.12
learning-embedding-adaptation-for-few-shot	83.03
relational-embedding-for-few-shot	91.11
learning-to-learn-by-self-critique	85.63
easy-ensemble-augmented-shot-y-shaped	91.93
exploiting-unsupervised-inputs-for-accurate	92.14
self-supervised-learning-for-few-shot-image	89.18
mergednet-a-simple-approach-for-one-shot	83.42
learning-to-compare-relation-network-for-few	65.32