Video captioning is a challenging task of modelling the objects, their temporal information and interaction in order to generate a textual description. Current models often fail to model these objects and their interactions correctly, due to lack of knowledge about them.
We present an empirical study of debiasing methods for classifiers, showing that debiasers often fail in practice to generalize out-of-sample, and can in fact make fairness worse rather than better.
We study the effects of different debiasing methods on the underlying causal path specific effects (PSEs) and explain these effects using an information-theoretic perspective.
We present Fairness.jl, a comprehensive bias audit and mitigation toolkit in julia. Extensive support and functionality provided by MLJ.jl has been used in this package.