Object localization in ImageNet by looking out of the window
This addresses the challenge of accurately locating objects in large-scale image datasets like ImageNet, offering an incremental advancement over prior window-scoring methods.
The paper tackles the problem of object localization in ImageNet by proposing a method that scores candidate windows based on their context with other windows, rather than independently, and demonstrates significant improvement over existing techniques on 92,000 images.
We propose a method for annotating the location of objects in ImageNet. Traditionally, this is cast as an image window classification problem, where each window is considered independently and scored based on its appearance alone. Instead, we propose a method which scores each candidate window in the context of all other windows in the image, taking into account their similarity in appearance space as well as their spatial relations in the image plane. We devise a fast and exact procedure to optimize our scoring function over all candidate windows in an image, and we learn its parameters using structured output regression. We demonstrate on 92000 images from ImageNet that this significantly improves localization over recent techniques that score windows in isolation.