Image Clustering On Cifar 10

평가 지표

ARI

Accuracy

Backbone

NMI

Train set

평가 결과

이 벤치마크에서 각 모델의 성능 결과

비교 표

모델 이름	ARI	Accuracy	Backbone	NMI	Train set
clustering-friendly-representation-learning-1	0.663	0.815	ResNet-18	0.711	Train+Test
auto-encoding-variational-bayes	0.168	0.291	VAE	0.245	Train+Test
information-maximization-clustering-via-multi	0.8	0.897	ResNet-18	0.818	Train
exploring-a-principled-framework-for-deep	-	0.972	-	0.928	-
unsupervised-deep-embedding-for-clustering	0.161	0.301	Custom	0.25	Train+Test
learning-to-classify-images-without-labels	0.758	0.876	ResNet-18	0.787	Train
joint-unsupervised-learning-of-deep	0.138	0.272	-	0.192	Train+Test
unsupervised-representation-learning-with-1	0.176	0.315	GAN	0.265	Train+Test
learning-to-classify-images-without-labels	0.772	0.883	ResNet-18	0.797	Train
let-go-of-your-labels-with-unsupervised-1	0.989	0.995	-	0.985	-
unsupervised-visual-representation-learning-3	0.732	0.857	ResNet-18	0.766	Train
multi-modal-deep-clustering-unsupervised	-	0.820	ResNet18	0.703	-
image-clustering-with-external-guidance	0.831	0.919	-	0.833	-
dhog-deep-hierarchical-object-grouping	0.492	0.666	ResNet-18	0.585	Train+Test
contrastive-hierarchical-clustering	0.731	0.839	ResNet-50	0.779	Train
breaking-the-reclustering-barrier-in-centroid	0.812	0.906	ResNet-18	0.826	Train
breaking-the-reclustering-barrier-in-centroid	0.818	0.907	ResNet-18	0.833	Train
improving-unsupervised-image-clustering-with	-	0.903	ResNet-18	-	-
information-maximization-clustering-via-multi	0.79	0.891	ResNet-18	0.811	Train
deep-adaptive-image-clustering	0.301	0.522	ConvNet	0.4	Train+Test
deep-clustering-via-probabilistic-ratio-cut	-	0.975	-	0.934	-
breaking-the-reclustering-barrier-in-centroid	0.824	0.912	ResNet-18	0.837	Train
모델 23	-	0.325	ResNet	-	Train+Test
stable-cluster-discrimination-for-deep-1	0.857	0.93	ResNet-18	0.861	Train
the-balanced-pairwise-affinities-feature	0.866	0.933	ResNet-18	0.870	-
contrastive-clustering	0.637	0.79	ResNet34	0.705	Train+Test
representation-learning-for-clustering-via	0.715	0.846	-	0.762	Train
the-single-noun-prior-for-image-clustering	0.702	0.853	ViT-B-32	0.731	Train+Test
deep-clustering-for-unsupervised-learning-of	-	0.374	ResNet-34	-	Train+Test
c3-cross-instance-guided-contrastive	0.707	0.838	-	0.748	-
exploring-the-limits-of-deep-image-clustering	0.885	0.94.5	ViT-B	0.886	Train
모델 32	0.776	0.884	ResNet-18	-	Train
deep-comprehensive-correlation-mining-for	0.408	0.623	AlexNet	0.496	Train+Test
spice-semantic-pseudo-labeling-for-image	0.836	0.918	ResNet-18	0.850	Train
invariant-information-distillation-for	0.411	0.617	ResNet-34	0.511	Train+Test
improving-image-clustering-with-artifacts	0.7946	0.8449	ViT-B/14	0.8682	Test
exploring-the-limits-of-deep-image-clustering	0.932	0.969	ViT-L	0.926	Train
twin-contrastive-learning-for-online	0.780	0.887	ResNet-34	0.819	Train
mitigating-embedding-and-class-assignment	-	0.81	ResNet-18	-	Train
deep-probability-aggregation-clustering	0.866	0.934	ResNet-34	0.87	-