paper-with-me

Papers

Unsupervised learning of object landmarks by factorized spatial embeddings

2017-05-05 · ICCV 2017 10 · James Thewlis, Hakan Bilen, Andrea Vedaldi

Learning automatically the structure of object categories remains an important open problem in computer vision. In this paper, we propose a novel unsupervised approach that can discover and learn landmarks in object categories, thus characterizing their structure. Our approach is based on factorizing image deformations, as induced by a viewpoint change or an object deformation, by learning a deep neural network that detects landmarks consistently with such visual effects. Furthermore, we show that the learned landmarks establish meaningful correspondences between different object instances in a category without having to impose this requirement explicitly. We assess the method qualitatively on a variety of object types, natural and man-made. We also show that our unsupervised landmarks are highly predictive of manually-annotated landmarks in face benchmark datasets, and can be used to regress these with a high degree of accuracy.

📄 PDF Abstract BibTeX arXiv:1705.02193

Code (1)

alldbi/Factorized-Spatial-Embeddings tf

Tasks

ObjectUnsupervised Facial Landmark DetectionUnsupervised Human Pose EstimationUnsupervised Keypoints

Similar Papers 제목 키워드 기반

Unsupervised Disentanglement of Pose, Appearance and Background from Images and Videos

2020-01-26 · Aysegul Dundar, Kevin J. Shih, Animesh Garg, Robert Pottorf 외

Unsupervised landmark learning is the task of learning semantic keypoint-like representations without the use of expensive input keypoint-level annotations. A popular approach is to factorize an image into a pose and app…

DisentanglementVideo Prediction

Unsupervised Learning of Object Landmarks via Self-Training Correspondence

2020-12-01 · NeurIPS 2020 12 · Dimitrios Mallis, Enrique Sanchez, Matthew Bell, Georgios Tzimiropoulos

This paper addresses the problem of unsupervised discovery of object landmarks. We take a different path compared to that of existing works, based on 2 novel perspectives: (1) Self-training: starting from generic keypoin…

ClusteringObjectUnsupervised Landmark Detection

Unsupervised Discovery of Facial Landmarks and Head Pose

2025-01-01 · CVPR 2025 1 · Satyajit Tourani, Siddharth Tourani, Arif Mahmood, Muhammad Haris Khan

Unsupervised landmark and head pose estimation is fundamental in fields like biometrics, augmented reality, and emotion recognition, offering accurate spatial data without relying on labeled datasets. It enhances sca…

Emotion RecognitionHead Pose EstimationLandmark TrackingPose Estimation+1

SPACE: Unsupervised Object-Oriented Scene Representation via Spatial Attention and Decomposition

2020-01-08 · ICLR 2020 1 · Zhixuan Lin, Yi-Fu Wu, Skand Vishwanath Peri, Weihao Sun 외

The ability to decompose complex multi-object scenes into meaningful abstractions like objects is fundamental to achieve higher-level cognition. Previous approaches for unsupervised object-oriented scene representation l…

ObjectRepresentation Learning

Unsupervised Discovery of Object Landmarks as Structural Representations

2018-04-12 · CVPR 2018 6 · Yuting Zhang, Yijie Guo, Yixin Jin, Yijun Luo 외

Deep neural networks can model images with rich latent representations, but they cannot naturally conceptualize structures of object categories in a human-perceptible way. This paper addresses the problem of learning obj…

ObjectUnsupervised Facial Landmark DetectionUnsupervised Human Pose EstimationUnsupervised Keypoint Estimation