Aiming at the problem of target detection under the condition of small samples, the current target detection methods under the condition of small samples are summarized. This paper lists four kinds of small sample learning methods, introduces their advantages and disadvantages, and introduces the typical algorithms of these methods at present; carries out the experimental design of small sample target detection, and obtains the application direction by analyzing the characteristics of each method; discusses the existing problems of current small sample image target detection. The results show that the analysis can provide more ideas for researchers in related fields.