Semantic Segmentation On Pascal Context
评估指标
mIoU
评测结果
各个模型在此基准测试上的表现结果
比较表格
| 模型名称 | mIoU |
|---|---|
| context-encoding-for-semantic-segmentation | 51.7 |
| 190807919 | 54 |
| condnet-conditional-classifier-for-scene | 57 |
| vision-transformer-adapter-for-dense | 68.2 |
| segvit-semantic-segmentation-with-plain | 65.3 |
| resnest-split-attention-networks | 58.4 |
| object-contextual-representations-for | 56.2 |
| dual-graph-convolutional-network-for-semantic | 53.7 |
| caa-channelized-axial-attention-for-semantic | 60.5 |
| location-aware-upsampling-for-semantic | 53.9 |
| minimalist-and-high-performance-semantic | 71.0 |
| car-class-aware-regularizations-for-semantic-1 | 64.1 |
| convolutional-feature-masking-for-joint | 34.4 |
| deeplab-semantic-image-segmentation-with-deep | 45.7 |
| internimage-exploring-large-scale-vision | 70.3 |
| efficient-yet-deep-convolutional-neural | 42.6 |
| object-contextual-representations-for | 59.6 |
| asymmetric-non-local-neural-networks-for | 52.8 |
| efficient-self-ensemble-framework-for-1 | 56.6 |
| bridging-category-level-and-instance-level | 44.5 |
| conditional-random-fields-as-recurrent-neural-1 | 39.3 |
| efficient-self-ensemble-framework-for-1 | 64.0 |
| the-devil-is-in-the-labels-semantic | 54.2 |
| generalized-parametric-contrastive-learning | 56.2 |
| co-occurrent-features-in-semantic | 54.0 |
| segclip-patch-aggregation-with-learnable | 24.7 |
| scene-parsing-via-integrated-classification | 52.60 |
| sequential-ensembling-for-semantic | 62.1 |
| rethinking-decoders-for-transformer-based | 57.9 |
| region-based-semantic-segmentation-with-end | 32.5 |
| boxsup-exploiting-bounding-boxes-to-supervise | 40.5 |
| context-prior-for-scene-segmentation | 53.9 |
| rethinking-decoders-for-transformer-based | 58.6 |
| is-attention-better-than-matrix-decomposition-1 | 55.2 |
| fastfcn-rethinking-dilated-convolution-in-the | 53.1 |
| dual-attention-network-for-scene-segmentation | 52.6 |
| caa-channelized-axial-attention-for-semantic | 60.1 |
| vision-transformer-adapter-for-dense | 67.5 |
| fully-convolutional-networks-for-semantic-1 | 37.8 |
| object-contextual-representations-for | 54.8 |
| scene-segmentation-with-dual-relation-aware | 55.4% |
| expectation-maximization-attention-networks | 53.1 |
| caa-channelized-axial-attention-for-semantic | 55.0 |
| pyramid-scene-parsing-network | 47.8 |
| resnest-split-attention-networks | 58.9 |
| boundary-aware-feature-propagation-for-scene | 53.6 |
| condnet-conditional-classifier-for-scene | 56.0 |
| representation-separation-for-semantic | 68.9 |
| vision-transformers-for-dense-prediction | 60.46 |
| parsenet-looking-wider-to-see-better | 40.4 |
| representation-separation-for-semantic | 67.5 |
| higher-order-conditional-random-fields-in | 41.3 |
| dcnas-densely-connected-neural-architecture | 55.6 |
| co-occurrent-features-in-semantic | 51.5 |
| wider-or-deeper-revisiting-the-resnet-model | 48.1 |
| refinenet-multi-path-refinement-networks-for | 47.3 |
| segmenter-transformer-for-semantic | 59.0 |
| efficient-piecewise-training-of-deep | 43.3 |
| cassod-net-cascaded-and-separable-structures | 52.76 |
| rethinking-semantic-segmentation-from-a | 55.83 |
| decoders-matter-for-semantic-segmentation | 52.5 |
| disentangled-non-local-neural-networks | 55.3 |
| semantic-correlation-promoted-shape-variant-1 | 53.2 |
| vpnext-rethinking-dense-decoding-for-plain | 71.1 |
| resnest-split-attention-networks | 56.5 |
| 190807919 | 54.0 |