EMSANet (2x ResNet-34 NBt1D, PanopticNDT version, finetuned)

Reported on 5 benchmarks across 3 tasks · 1 paper · 5 SOTA

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

Medical2 results

Semantic SegmentationonNYU Depth v2
Mean IoU· 2023-09-24
59.02
best: 63.6 (OmniVec2)
SOTA
PanopticNDT: Efficient and Robust Panoptic Mapping arXiv:2309.13635
Semantic SegmentationonNYU Depth v2
PQ· 2023-09-24
51.15
SOTA
PanopticNDT: Efficient and Robust Panoptic Mapping arXiv:2309.13635

Audio2 results

10-shot image generationonNYU Depth v2
Mean IoU· 2023-09-24
59.02
best: 63.6 (OmniVec2)
SOTA
PanopticNDT: Efficient and Robust Panoptic Mapping arXiv:2309.13635
10-shot image generationonNYU Depth v2
PQ· 2023-09-24
51.15
SOTA
PanopticNDT: Efficient and Robust Panoptic Mapping arXiv:2309.13635

Computer Vision1 result

Panoptic SegmentationonNYU Depth v2
PQ· 2023-09-24
51.15
SOTA
PanopticNDT: Efficient and Robust Panoptic Mapping arXiv:2309.13635