Many fast search strategies reduce the complexity of motion estimation by limiting search locations, including the center-biased diamond search (DS), which performances better for small motion, and the nonbiased three step search (TSS), which works better for large motion. To achieve improved performance, we propose a diversity search strategy (DSS) by combining DS and TSS and applying them to decimated block matching error functions. The diversity in search strategies and self-similarity of the decimated error functions can overcome the disadvantages of individual search without increasing the computational complexity. Extensive simulations show that DSS approaches the performance of full-search and outperforms individual strategies. Based on DSS, and efficient adaptive DSS (ADSS) is proposed. It is shown to outperform DS and TSS, both in quality and complexity. Finally, a fast motion estimation using diversity in matching criteria (DMC) is presented, with potential applications for variable-block-size motion estimation.