DeepLabV3+ (ResNet-101)

Reported on 4 benchmarks across 2 tasks · 1 paper · 2 SOTA

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

Medical2 results

Semantic SegmentationonPASCAL VOC 2012 val
mIoU (Syn)· 2018-02-07
75.39
SOTA
Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation arXiv:1802.02611
Semantic SegmentationonUrbanLF
mIoU (Real)· 2018-02-07
76.27
best: 83.22 (CMNeXt (RGB-LF8))
Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation arXiv:1802.02611

Audio2 results

10-shot image generationonPASCAL VOC 2012 val
mIoU (Syn)· 2018-02-07
75.39
SOTA
Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation arXiv:1802.02611
10-shot image generationonUrbanLF
mIoU (Real)· 2018-02-07
76.27
best: 83.22 (CMNeXt (RGB-LF8))
Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation arXiv:1802.02611