Poster
Unsupervised Learning of Object Landmarks through Conditional Image Generation
Tomas Jakab · Ankush Gupta · Hakan Bilen · Andrea Vedaldi
Room 517 AB #112
Keywords: [ Deep Learning ] [ Unsupervised Learning ] [ Deep Autoencoders ] [ Computer Vision ] [ Generative Models ] [ Representation Learning ] [ Embedding Approaches ] [ Visual Features ] [ CNN Architectures ] [ Body Pose, Face, and Gesture Analysis ]
We propose a method for learning landmark detectors for visual objects (such as the eyes and the nose in a face) without any manual supervision. We cast this as the problem of generating images that combine the appearance of the object as seen in a first example image with the geometry of the object as seen in a second example image, where the two examples differ by a viewpoint change and/or an object deformation. In order to factorize appearance and geometry, we introduce a tight bottleneck in the geometry-extraction process that selects and distils geometry-related features. Compared to standard image generation problems, which often use generative adversarial networks, our generation task is conditioned on both appearance and geometry and thus is significantly less ambiguous, to the point that adopting a simple perceptual loss formulation is sufficient. We demonstrate that our approach can learn object landmarks from synthetic image deformations or videos, all without manual supervision, while outperforming state-of-the-art unsupervised landmark detectors. We further show that our method is applicable to a large variety of datasets - faces, people, 3D objects, and digits - without any modifications.
Live content is unavailable. Log in and register to view live content