SED

Reported on 6 benchmarks across 3 tasks · 1 paper

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

Computer Vision5 results

Open Vocabulary Semantic SegmentationonADE20K-847
mIoU· 2023-11-27
13.9
best: 17.3 (UMG-CLIP-E/14)
SED: A Simple Encoder-Decoder for Open-Vocabulary Semantic Segmentation arXiv:2311.15537
Open Vocabulary Semantic SegmentationonPASCAL Context-459
mIoU· 2023-11-27
22.6
best: 25.8 (SILC)
SED: A Simple Encoder-Decoder for Open-Vocabulary Semantic Segmentation arXiv:2311.15537
Open Vocabulary Semantic SegmentationonPASCAL Context-59
mIoU· 2023-11-27
60.6
best: 64.6 (HyperSeg)
SED: A Simple Encoder-Decoder for Open-Vocabulary Semantic Segmentation arXiv:2311.15537
Open Vocabulary Semantic SegmentationonADE20K-150
mIoU· 2023-11-27
35.2
best: 38.2 (Mask-Adapter)
SED: A Simple Encoder-Decoder for Open-Vocabulary Semantic Segmentation arXiv:2311.15537
Edge DetectiononCID
ODS
0.65

Methodology1 result

2D Object DetectiononCID
ODS
0.65