4 papers
Benchmarking NACTI Species Recognition in Long-Tailed Regimes
Zehua Liu, Tilo Burghardt
As with most ``in the wild'' collections of the natural world, the North America Camera Trap Images (NACTI) dataset exhibits long-tailed class imbalance, with the largest class cov…
Long-tailed Species Recognition in the NACTI Wildlife Dataset
Zehua Liu, Tilo Burghardt
As most ''in the wild'' data collections of the natural world, the North America Camera Trap Images (NACTI) dataset shows severe long-tailed class imbalance, noting that the larges…
Decoupling Training-Free Guided Diffusion by ADMM
Youyuan Zhang, Zehua Liu, Zenan Li +3
In this paper, we consider the conditional generation problem by guiding off-the-shelf unconditional diffusion models with differentiable loss functions in a plug-and-play fashion.…
Full Bayesian Significance Testing for Neural Networks
Zehua Liu, Zimeng Li, Jingyuan Wang +1
Significance testing aims to determine whether a proposition about the population distribution is the truth or not given observations. However, traditional significance testing oft…