Transfer learning makes use of data or knowledge in one task to help solve a different, yet related, task. Many ex isting TL approaches are based on a joint probability distribution metric, which is a weighted sum of the marginal distribution and the c ondi-tional distribution; however, they optimize the two distri butions independently, and ignore their intrinsic dependency. This p aper proposes a novel and frustratingly easy Joint Probability Dist ribution Adaptation (JPDA) approach, to replace the frequently-use d joint maximum mean discrepancy metric in transfer learning. Duri ng the distribution adaptation, JPDA improves the transferabili ty between the source and the target domains by minimizing the joint pro b-ability discrepancy of the corresponding class, and also in creases the discriminability between different classes by maximiz ing their joint probability discrepancy. Experiments on six image cl assifica-tion datasets demonstrated that JPDA outperforms several s tate-of- the-art metric-based transfer learning approaches.