Abstract Deep ConvNets have shown great performance for single-label image classifification (e.g. ImageNet), but it is necessary to move beyond the single-label classifification task because pictures of everyday life are inherently multilabel. Multi-label classifification is a more diffificult task than single-label classifification because both the input images and output label spaces are more complex. Furthermore, collecting clean multi-label annotations is more diffificult to scale-up than single-label annotations. To reduce the annotation cost, we propose to train a model with partial labels i.e. only some labels are known per image. We fifirst empirically compare different labeling strategies to show the potential for using partial labels on multi-label datasets. Then to learn with partial labels, we introduce a new classifification loss that exploits the proportion of known labels per example. Our approach allows the use of the same training settings as when learning with all the annotations. We further explore several curriculum learning based strategies to predict missing labels. Experiments are performed on three large-scale multi-label datasets: MS COCO, NUS-WIDE and Open Images.