Unsupervised Landmark Detection
5 papers with code • 1 benchmarks • 1 datasets
The discovery of object landmarks on a set of images depicting objects of the same category, directly from raw images without using any manual annotations.
Most implemented papers
Unsupervised Landmark Detection Based Spatiotemporal Motion Estimation for 4D Dynamic Medical Images
In the first stage, we process the raw dense image to extract sparse landmarks to represent the target organ anatomical topology and discard the redundant information that is unnecessary for motion estimation.
MBW: Multi-view Bootstrapping in the Wild
Our Multi-view Bootstrapping in the Wild (MBW) approach demonstrates impressive results on standard human datasets, as well as tigers, cheetahs, fish, colobus monkeys, chimpanzees, and flamingos from videos captured casually in a zoo.
Object landmark discovery through unsupervised adaptation
Contrary to previous works, we do however assume that a landmark detector, which has already learned a structured representation for a given object category in a fully supervised manner, is available.
Unsupervised Learning of Object Landmarks via Self-Training Correspondence
This paper addresses the problem of unsupervised discovery of object landmarks.
AutoLink: Self-supervised Learning of Human Skeletons and Object Outlines by Linking Keypoints
Our key ingredients are i) an encoder that predicts keypoint locations in an input image, ii) a shared graph as a latent variable that links the same pairs of keypoints in every image, iii) an intermediate edge map that combines the latent graph edge weights and keypoint locations in a soft, differentiable manner, and iv) an inpainting objective on randomly masked images.