Unsupervised Learning of Object Landmarks through Conditional Image Generation

Authors: Tomas Jakab, Ankush Gupta, Hakan Bilen, Andrea Vedaldi

NeurIPS 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental 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.
Researcher Affiliation Academia 1 Visual Geometry Group University of Oxford {tomj,ankush,vedaldi}@robots.ox.ac.uk 2 School of Informatics University of Edinburgh hbilen@ed.ac.uk
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks.
Open Source Code Yes Project code and details are available at: http://www.robots.ox.ac.uk/ ~vgg/research/unsupervised_landmarks/
Open Datasets Yes We use the 200k Celeb A [24] images after resizing them to 128 128 resolution. We consider Vox Celeb [28], a large dataset of face tracks... BBC-Pose [3], and Human3.6M [17]. Small NORB [26] dataset... SVHN digits [29]
Dataset Splits Yes Model selection is done using 10% validation split of the training data.
Hardware Specification No The paper does not provide specific details about the hardware used for running experiments.
Software Dependencies No The paper mentions optimizers and pre-trained models (e.g., Adam, VGG-19) but does not provide specific version numbers for software dependencies or frameworks.
Experiment Setup Yes The learning rate is set to 10 2, and lowered by a factor of 10 once the training error stops decreasing; the ℓ2-norm of the gradients is bounded to 1.0.