DeepLabv3 (ResNet-50)

Reported on 3 benchmarks across 1 task · 1 paper · 3 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Audio3 results

2D Semantic SegmentationonWildScenes
mIoU· uses extra data· 2017-06-17
43.37
best: 47.85 (Mask2Former (Swin-L))
SOTA
Rethinking Atrous Convolution for Semantic Image Segmentation arXiv:1706.05587
2D Semantic SegmentationonWildScenes
mIoU (Env DA)· uses extra data· 2017-06-17
36.12
SOTA
Rethinking Atrous Convolution for Semantic Image Segmentation arXiv:1706.05587
2D Semantic SegmentationonWildScenes
mIoU (Temporal DA) · uses extra data· 2017-06-17
43.95
SOTA
Rethinking Atrous Convolution for Semantic Image Segmentation arXiv:1706.05587