We address the problem of retrieving all the images containing a specific object in a large image collection, where the input query is given as a set of representative images of the object. This problem is referred to as multiple queries in the literature. For images described with bag-of-visual-words (BOW), one of the best performing approach amounts to simply averaging the query descriptors. This paper 1 introduces an improved fusion of the object description based on the recent concept of generalized max-pooling and memory vectors, which summarizes a set of vectors by a single representative vector. They have the property of reducing the influence of frequent features. Therefore , we propose to build a memory vector for each set of queries and the membership test is performed with each image descriptor from the database, to determine its similarity with the query representative. This new strategy for multiple queries brings a significant improvement for most of the image descriptors we have considered, in particular with Convolutional Neural Networks (CNN) features.