Abstract Multi-instance learning (MIL) has demonstrated its usefulness in many real-world image applications in recent years. However, two critical challenges prevent one from effectively using MIL in practice. First, existing MIL methods routinely model the predictive targets using the instances of input images, but rarely utilize an input image as a whole. As a result, the useful information conveyed by the holistic representation of an input image could be potentially lost. Second, the varied numbers of the instances of the input images in a data set make it infeasible to use traditional learning models that can only deal with single-vector inputs. To tackle these two challenges, in this paper we propose a novel image representation learning method that can integrate the local patches (the instances) of an input image (the bag) and its holistic representation into one single-vector representation. Our new method fifirst learns a projection to preserve both global and local consistencies of the instances of an input image. It then projects the holistic representation of the same image into the learned subspace for information enrichment. Taking into account the content and characterization variations in natural scenes and photos, we develop an objective that maximizes the ratio of the summations of a number of ℓ1-norm distances, which is diffificult to solve in general. To solve our objective, we derive a new effificient non-greedy iterative algorithm and rigorously prove its convergence. Promising results in extensive experiments have demonstrated improved performances of our new method that validate its effectiveness</