Poster

Exploring and Utilizing Pattern Imbalance

Shibin Mei · Chenglong Zhao · Shengchao Yuan · Bingbing Ni

West Building Exhibit Halls ABC 329

Abstract:

In this paper, we identify pattern imbalance from several aspects, and further develop a new training scheme to avert pattern preference as well as spurious correlation. In contrast to prior methods which are mostly concerned with category or domain granularity, ignoring the potential finer structure that existed in datasets, we give a new definition of seed category as an appropriate optimization unit to distinguish different patterns in the same category or domain. Extensive experiments on domain generalization datasets of diverse scales demonstrate the effectiveness of the proposed method.

Chat is not available.