Since there are many different object domains in the world, e.g., landmarks, products, or artworks, capturing all of them in a single dataset and training a model that can distinguish between them is quite a challenging task. Finally, the representation was used to solve the ILR tasks related to classification (e.g., with a shallow classifier trained on top of the embedding) or retrieval (e.g., with a nearest neighbor search in the embedding space). Then a deep model was trained to embed each image into a high-dimensional space where similar images have similar representations. First, a large set of images was collected. Previously, ILR was tackled using deep learning approaches. One challenging type of computer vision problem is instance-level recognition (ILR) - given an image of an object, the task is to not only determine the generic category of an object (e.g., an arch), but also the specific instance of the object (”Arc de Triomphe de l'Étoile, Paris, France”). Posted by Bingyi Cao, Software Engineer, Google Research, and Mário Lipovský, Software Engineer, Google LensĬomputer vision models see daily application for a wide variety of tasks, ranging from object recognition to image-based 3D object reconstruction.