Paper-Reading

Introduction

Links:

Visual Domain Adaptation Challenge:

  1. Feature Level
    • align the features extracted from the networks across the sourse and the target domains. (Unsupervised: no labeled target samples)
    • typically, minimize some measure of the distance between the source and the target feature distribution,
    • maximum mean discrepency:
    • Correlation distance
    • adversarial discriminator accuracy - Limitaions:
      1. align marginal distributions does not enforce any semantic consistency. (e.g. car->bicycle) If the feature distributions are quite different??
      2. higher levels of a deep representation can fail to model aspects of low-level appearance variance lose some low-level/local feature/information
  2. ** Pixel/Frame Level** : Generative
    • similar distribution alignment. Translate the source data to the style of a target domain. similar distribution alignment: If the feature distributions are quite different??
    • Unsupervised methods:
    • Limiation:
    • small image sizes and limited domain shifts;
    • controlled enveironment;
    • may not preserve content: crucial semantic information may be lost - Multilevel