Few Shot Semantic Segmentation On Pascal 5I 1
Metrics
Mean IoU
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | Mean IoU |
|---|---|
| clustered-patch-element-connection-for-few | 60.5 |
| dense-gaussian-processes-for-few-shot | 64.8 |
| dense-cross-query-and-support-attention | 69.3 |
| bridge-the-points-graph-based-few-shot | 72.1 |
| interclass-prototype-relation-for-few-shot | 65.7 |
| pyramid-graph-networks-with-connection | 56.0 |
| iterative-few-shot-semantic-segmentation-from | 61.1 |
| adaptive-prototype-learning-and-allocation | 59.31 |
| hmfs-hybrid-masking-for-few-shot-segmentation | 65.8 |
| apanet-adaptive-prototypes-alignment-network | 64 |
| doubly-deformable-aggregation-of-covariance | 67.5 |
| hierarchical-dense-correlation-distillation | 65.1 |
| doubly-deformable-aggregation-of-covariance | 65.7 |
| fecanet-boosting-few-shot-semantic | 64.3 |
| hybrid-mamba-for-few-shot-segmentation | 67.3 |
| visual-and-textual-prior-guided-mask-assemble | 74.1 |
| few-shot-segmentation-without-meta-learning-a | 59.7 |
| seggpt-segmenting-everything-in-context | 83.2 |
| mianet-aggregating-unbiased-instance-and-1 | 68.72 |
| msdnet-multi-scale-decoder-for-few-shot | 64.7 |
| feature-proxy-transformer-for-few-shot | 68.8 |
| quaternion-valued-correlation-learning-for | 64.3 |
| few-shot-semantic-segmentation-with-support | 60.8 |
| doubly-deformable-aggregation-of-covariance | 66.8 |
| self-calibrated-cross-attention-network-for | 68.3 |
| panet-few-shot-image-semantic-segmentation | 48.1 |
| self-calibrated-cross-attention-network-for | 66.8 |
| doubly-deformable-aggregation-of-covariance | 61.8 |
| adaptive-prototype-learning-and-allocation | 59.29 |
| diffss-diffusion-model-for-few-shot-semantic | 70.2 |
| quaternion-valued-correlation-learning-for | 60.6 |
| masked-cross-image-encoding-for-few-shot | 65.93 |
| intermediate-prototype-mining-transformer-for | 66.1 |
| hybrid-mamba-for-few-shot-segmentation | 70.4 |
| quaternion-valued-correlation-learning-for | 67 |
| hypercorrelation-squeeze-for-few-shot | 64.0 |
| few-shot-segmentation-without-meta-learning-a | 59.4 |
| simpler-is-better-few-shot-semantic | 58 |
| eliminating-feature-ambiguity-for-few-shot | 70.3 |
| msanet-multi-similarity-and-attention-1 | 69.13 |
| prototype-as-query-for-few-shot-semantic | 63.2 |
| visual-and-textual-prior-guided-mask-assemble | 77.6 |
| diffss-diffusion-model-for-few-shot-semantic | 66.2 |
| integrative-few-shot-learning-for | 66.9 |
| prior-guided-feature-enrichment-network-for | 60.1 |
| singular-value-fine-tuning-few-shot-1 | 64.87 |
| self-guided-and-cross-guided-learning-for-few | 61.8 |
| dense-cross-query-and-support-attention | 64.6 |
| simpler-is-better-few-shot-semantic | 56.4 |
| cost-aggregation-with-4d-convolutional-swin | 67.9 |
| hypercorrelation-squeeze-for-few-shot | 66.2 |
| dense-gaussian-processes-for-few-shot | 63.5 |
| visual-and-textual-prior-guided-mask-assemble | 74.1 |
| prior-guided-feature-enrichment-network-for | 58 |
| few-shot-segmentation-via-cycle-consistent | 64.3 |
| diffss-diffusion-model-for-few-shot-semantic | 69.3 |
| msanet-multi-similarity-and-attention-1 | 68.52 |
| doubly-deformable-aggregation-of-covariance | 69.1 |
| singular-value-fine-tuning-few-shot-1 | 68.95 |
| self-guided-and-cross-guided-learning-for-few | 57.5 |
| mining-latent-classes-for-few-shot | 63.8 |
| prototype-mixture-models-for-few-shot | 56.3 |
| dense-cross-query-and-support-attention | - |
| singular-value-fine-tuning-few-shot-1 | 68.15 |
| hmfs-hybrid-masking-for-few-shot-segmentation | 67.8 |
| feature-weighting-and-boosting-for-few-shot | 51.9 |
| self-support-few-shot-semantic-segmentation | 61.4 |
| learning-what-not-to-segment-a-new | 67.81 |
| feature-weighting-and-boosting-for-few-shot | 56.2 |
| hmfs-hybrid-masking-for-few-shot-segmentation | 65 |
| interclass-prototype-relation-for-few-shot | 67.5 |
| msdnet-multi-scale-decoder-for-few-shot | 64.3 |
| cost-aggregation-with-4d-convolutional-swin | 65.5 |
| mianet-aggregating-unbiased-instance-and-1 | 67.63 |
| prototype-as-query-for-few-shot-semantic | 63.1 |
| a-new-local-transformation-module-for-few | 57.0 |
| hmfs-hybrid-masking-for-few-shot-segmentation | 66.7 |
| msanet-multi-similarity-and-attention-1 | 65.76 |
| eliminating-feature-ambiguity-for-few-shot | 66.6 |
| masked-cross-image-encoding-for-few-shot | 62.87 |
| feature-proxy-transformer-for-few-shot | 64.7 |
| anti-aliasing-semantic-reconstruction-for-few | 58.16 |
| sg-one-similarity-guidance-network-for-one | 46.3 |
| cost-aggregation-is-all-you-need-for-few-shot | 67.5 |
| dynamic-prototype-convolution-network-for-few | 66.7 |
| iterative-few-shot-semantic-segmentation-from | 56.5 |
| self-support-few-shot-semantic-segmentation | 64.6 |
| few-shot-semantic-segmentation-with-support | 65.7 |
| part-aware-prototype-network-for-few-shot | 51.5 |
| msi-maximize-support-set-information-for-few | 70.1 |
| hypercorrelation-squeeze-for-few-shot | 59.7 |
| beyond-the-prototype-divide-and-conquer | 62.80 |
| singular-value-fine-tuning-few-shot-1 | 64.33 |
| apanet-adaptive-prototypes-alignment-network | 59 |
| clustered-patch-element-connection-for-few | 60.4 |
| hierarchical-dense-correlation-distillation | 69.4 |
| anti-aliasing-semantic-reconstruction-for-few | 55.66 |
| mianet-aggregating-unbiased-instance-and-1 | 67.10 |
| few-shot-semantic-segmentation-with-support | 65.3 |
| intermediate-prototype-mining-transformer-for | 66.8 |
| canet-class-agnostic-segmentation-networks | 55.4 |
| mining-latent-classes-for-few-shot | 63.6 |
| prior-guided-feature-enrichment-network-for | 60.8 |
| apanet-adaptive-prototypes-alignment-network | 63 |
| fecanet-boosting-few-shot-semantic | 67.4 |