← Back to papers
2006 NIPS NeurIPS 2006

Clustering appearance and shape by learning jigsaws

Abstract

Patch-based appearance models are used in a wide range of computer vision ap- plications. To learn such models it has previously been necessary to specify a suitable set of patch sizes and shapes by hand. In the jigsaw model presented here, the shape, size and appearance of patches are learned automatically from the repeated structures in a set of training images. By learning such irregularly shaped ‘jigsaw pieces’, we are able to discover both the shape and the appearance of object parts without supervision. When applied to face images, for example, the learned jigsaw pieces are surprisingly strongly associated with face parts of different shapes and scales such as eyes, noses, eyebrows and cheeks, to name a few. We conclude that learning the shape of the patch not only improves the accuracy of appearance-based part detection but also allows for shape-based part detection. This enables parts of similar appearance but different shapes to be dis- tinguished; for example, while foreheads and cheeks are both skin colored, they have markedly different shapes.

🚀 Conference Pioneer — NIPS 2006
🌉 Interdisciplinary Bridge — Computer Vision and Machine Learning
📈 Trend Setter — Semantic Segmentation
🧭 Keyword Pioneer — shape analysis
🐝 Cross-Pollinator — Artificial Intelligence, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning
🐣 Hot Topic Early Bird — image segmentation

Authors

Anitha Kannan , John Winn , Carsten Rother

Topics

Machine Learning > Core Methods > Clustering Machine Learning > Learning Types > Unsupervised Learning Computer Vision > Analysis > Scene Understanding Computer Vision > Analysis > Semantic Segmentation Computer Vision > Processing > Image Processing Machine Learning > Learning Paradigms > Unsupervised Learning Computer Vision > Analysis > Computer Vision

Keywords

unsupervised learning image segmentation feature learning clustering unsupervised clustering shape analysis appearance modeling object detection patch-based model appearance model shape detection part detection shape recognition jigsaw puzzle shape learning patch-based appearance model object parts detection
Download PDF

Related papers

Temporal Coding using the Response Properties of Spiking Neurons 2006
Parameter Expanded Variational Bayesian Methods 2006
Effects of Stress and Genotype on Meta-parameter Dynamics in Reinforcement Learning 2006
Ordinal Regression by Extended Binary Classification 2006
Blind source separation for over-determined delayed mixtures 2006