INSTRE stands for INSTance-level visual object REtrieval and REcognition. It is an image dataset used to verify instance-level object retrieval, recognition algorithms and other machine vision algorithms such as detection, invariant features, and feature matching. The dataset is divided into three disjoint subsets. INSTRE-S1 and INSTRE-S2 are collected for measuring single target cases, both of which have 100 object classes. INSTRE-S1 contains 11,011 images and INSTRE-S2 contains 12,059 images. INSTRE-M targets multi-target cases.