Domain Generalization On Pacs 2
المقاييس
Average Accuracy
النتائج
نتائج أداء النماذج المختلفة على هذا المعيار القياسي
جدول المقارنة
| اسم النموذج | Average Accuracy |
|---|---|
| simple-specialized-model-sample-matching-for | 88.6 |
| global-local-regularization-via | 73.5 |
| sparse-fusion-mixture-of-experts-are-domain | 88.1 |
| batch-normalization-embeddings-for-deep-1 | 83.1 |
| distributionally-robust-neural-networks-for | 84.4 |
| decaug-out-of-distribution-generalization-via | 82.39 |
| domain-separation-networks | 67.37 |
| ensemble-of-averages-improving-model | 95.8 |
| multi-component-image-translation-for-deep | 69.45 |
| learning-to-balance-specificity-and | 81.46 |
| deeper-broader-and-artier-domain | 58.74 |
| decaug-augmenting-hoi-detection-via | 82.4 |
| soft-prompt-generation-for-domain | 97.0 |
| fishr-invariant-gradient-variances-for-out-of | 86.9 |
| nas-ood-neural-architecture-search-for-out-of | 84.23 |
| rethinking-multi-domain-generalization-with-a | 97.9 |
| rethinking-multi-domain-generalization-with-a | 88.4 |
| domain-generalization-via-entropy | 81.38 |
| cross-domain-ensemble-distillation-for-domain | 86.4 |
| domain-generalization-with-adversarial | 77.0 |
| a-style-and-semantic-memory-mechanism-for-1 | 86.6 |
| soft-prompt-generation-for-domain | 92.8 |
| domain-aware-triplet-loss-in-domain | 87.3 |
| domain-generalization-using-causal-matching-1 | 84.35 |
| self-challenging-improves-cross-domain | 87.83 |
| distilling-from-vision-language-models-for | 96.68 |
| deeper-broader-and-artier-domain | 58.99 |
| deep-domain-generalization-via-conditional | 82.6 |
| domain-generalization-with-mixstyle-1 | 83.7 |
| towards-recognizing-unseen-categories-in | 81.6 |
| promptstyler-prompt-driven-style-generation | 98.6 |
| domain-generalization-by-solving-jigsaw | 73.38 |
| domain-aware-triplet-loss-in-domain | 97.6 |
| discriminative-adversarial-domain | 80.38 |
| out-of-distribution-generalization-via-risk | 71.14 |
| weight-averaging-improves-knowledge | 87.6 |
| recycling-diverse-models-for-out-of | 90.5 |
| learning-to-generalize-meta-learning-for | 70.01 |
| rethinking-domain-generalization-baselines | 77.31 |
| in-search-of-lost-domain-generalization | 85.50 |
| domain-generalization-via-model-agnostic | 81.04 |
| learning-to-optimize-domain-specific | 86.64 |
| learning-to-optimize-domain-specific | 85.11 |
| domain-generalization-needs-stochastic-weight | 88.1 |
| promptstyler-prompt-driven-style-generation | 97.2 |
| vne-an-effective-method-for-improving-deep | 88.3 |
| towards-unified-and-effective-domain | 95.6 |
| domain-generalization-using-large-pretrained | 97.4 |
| rethinking-multi-domain-generalization-with-a | 97.3 |
| self-supervised-learning-across-domains | 74.08 |
| deep-domain-generalization-via-conditional | 68.88 |
| unified-deep-supervised-domain-adaptation-and | 79.4 |
| domain-generalization-via-model-agnostic | 82.67 |
| deeper-broader-and-artier-domain | 69.21 |
| ensemble-of-averages-improving-model | 88.6 |
| learning-to-balance-specificity-and | 83.37 |
| domain-generalization-with-domain-specific | 71.20 |
| learning-from-extrinsic-and-intrinsic | 82.15 |
| domain-generalization-by-solving-jigsaw | 80.51 |
| cadg-a-model-based-on-cross-attention-for | 94.6 |
| learning-to-generate-novel-domains-for-domain | 82.8 |
| best-sources-forward-domain-generalization | 70.30 |
| adversarial-target-invariant-representation | 83.34 |
| learning-from-extrinsic-and-intrinsic | 85.84 |
| deep-domain-adversarial-image-generation-for | 83.1 |
| domain-generalization-by-solving-jigsaw | 79.05 |
| adversarial-target-invariant-representation | 73.55 |
| correlation-aware-adversarial-domain | 71.98 |
| deep-stable-learning-for-out-of-distribution | 84.69 |
| robust-and-generalizable-visual | 70.53 |
| domain-generalization-by-learning-and | 88.63 |
| self-challenging-improves-cross-domain | 85.15 |
| reducing-domain-gap-via-style-agnostic | 83.25 |
| cross-domain-ensemble-distillation-for-domain-2 | 86.4 |
| feature-critic-networks-for-heterogeneous | 70.40 |
| ensemble-of-averages-improving-model | 93.2 |
| domain-generalization-with-adversarial | 84.6 |
| qt-dog-quantization-aware-training-for-domain | 90.7 |
| efficient-domain-generalization-via-common | 80.69 |
| domain-generalization-with-domain-specific | 80.72 |
| rethinking-multi-domain-generalization-with-a | 85.6 |
| improve-unsupervised-domain-adaptation-with | 84.6 |
| simple-specialized-model-sample-matching-for | 99.0 |
| adaptive-methods-for-aggregated-domain | 89.2 |
| learning-robust-representations-by-projecting-1 | 70.20 |
| frustratingly-simple-domain-generalization | 84.64 |
| a-sentence-speaks-a-thousand-images-domain | 90.2 |
| generalizing-across-domains-via-cross | 80.7 |
| shape-biased-domain-generalization-via-shock | 47.45 |
| dynamic-domain-generalization | 87.87 |
| domain-generalization-via-model-agnostic | 75.21 |
| episodic-training-for-domain-generalization | 72.00 |
| selfreg-self-supervised-contrastive | 83.62 |
| improving-multi-domain-generalization-through | 87.35 |
| domain-generalization-via-entropy | 75.67 |
| 190513549 | 72.08 |
| النموذج 97 | 0 |
| domain-generalization-by-solving-jigsaw | 71.52 |
| frustratingly-simple-domain-generalization | 76.62 |
| domain-generalization-using-causal-matching-1 | 87.52 |
| sequential-learning-for-domain-generalization | 81.5 |
| towards-shape-biased-unsupervised | 79.15 |
| episodic-training-for-domain-generalization | 81.5 |
| reducing-domain-gap-via-style-agnostic | 82.3 |
| feature-alignment-and-restoration-for-domain | 81.7 |
| adaptive-methods-for-aggregated-domain | 87.0 |
| domain-generalization-by-mutual-information | 88.4 |
| context-aware-robust-fine-tuning | 96.8 |
| reducing-domain-gap-via-style-agnostic | 75.52 |
| domain-generalization-using-a-mixture-of | 74.38 |
| rethinking-domain-generalization-baselines | 84.32 |
| batchformer-learning-to-explore-sample | 88.6 |
| domain-generalization-using-a-mixture-of | 81.83 |
| qt-dog-quantization-aware-training-for-domain | 87.89 |
| meta-dmoe-adapting-to-domain-shift-by-meta | 86.9 |
| towards-shape-biased-unsupervised | 84.46 |
| metareg-towards-domain-generalization-using | 72.62 |
| self-challenging-improves-cross-domain | 85.2 |
| pcl-proxy-based-contrastive-learning-for | 88.7 |
| metareg-towards-domain-generalization-using | 81.7 |
| discriminative-adversarial-domain | 72.11 |
| improving-out-of-distribution-generalization | 69.32 |
| self-challenging-improves-cross-domain | 76.05 |
| self-supervised-learning-across-domains | 81.41 |
| domain-generalization-using-pretrained-models | 96.1 |
| domain-generalization-via-entropy | 85.34 |
| metareg-towards-domain-generalization-using | 83.6 |
| domain-generalization-by-mutual-information | 96.8 |
| weight-averaging-improves-knowledge | 86.6 |
| learning-to-balance-specificity-and | 73.32 |
| domain-generalization-using-pretrained-models | 84.1 |
| promptstyler-prompt-driven-style-generation | 93.2 |
| poem-polarization-of-embeddings-for-domain | 86.7 |