Model-agnostic Multi-Domain Learning with Domain-Specific Adapters for Action Recognition. (arXiv:2204.07270v2 [cs.CV] UPDATED)

In this paper, we propose a multi-domain learning model for action
recognition. The proposed method inserts domain-specific adapters between
layers of domain-independent layers of a backbone network. Unlike a multi-head
network that switches classification heads only, our model switches not only
the heads, but also the adapters for facilitating to learn feature
representations universal to multiple domains. Unlike prior works, the proposed
method is model-agnostic and doesn't assume model structures unlike prior
works. Experimental results on three popular action recognition …

arxiv model-agnostic