All in Tokens: Unifying Output Space of Visual Tasks via Soft Token
Open paper
Benchmark
Model
Rank
Results
monocular-depth-estimation-on-nyu-depth-v2
AiT-P(SwinV2-L)
#22
absolute relative error: 0.076
RMSE: 0.275
log 10: 0.033
…
Rank counts only results with a code link.