Trans4Trans

Reported on 4 benchmarks across 2 tasks · 2 papers · 2 SOTA

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

Medical2 results

Semantic SegmentationonDADA-seg
mIoU· uses extra data· 2021-08-20
39.2
best: 46.97 (MMUDA)
SOTA
Trans4Trans: Efficient Transformer for Transparent Object and Semantic Scene Segmentation in Real-World Navigation Assistance arXiv:2108.09174
Semantic SegmentationonEventScape
mIoU· 2021-07-07
51.86
best: 64.28 (CMX (B4))
Trans4Trans: Efficient Transformer for Transparent Object Segmentation to Help Visually Impaired People Navigate in the Real World arXiv:2107.03172

Audio2 results

10-shot image generationonDADA-seg
mIoU· uses extra data· 2021-08-20
39.2
best: 46.97 (MMUDA)
SOTA
Trans4Trans: Efficient Transformer for Transparent Object and Semantic Scene Segmentation in Real-World Navigation Assistance arXiv:2108.09174
10-shot image generationonEventScape
mIoU· 2021-07-07
51.86
best: 64.28 (CMX (B4))
Trans4Trans: Efficient Transformer for Transparent Object Segmentation to Help Visually Impaired People Navigate in the Real World arXiv:2107.03172