leon.bottou.org

User Tools

Site Tools

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

papers:lopezpaz-2017 [2017/06/22 16:35]
leonb created 		papers:lopezpaz-2017 [2017/06/22 16:42] (current)
leonb
Line 4: Line 4:
 //Abstract//: This paper establishes the existence of observable foot- prints that reveal the “causal dispositions” of the object categories appearing in collections of images. We achieve this goal in two steps. First, we take a learning approach to observational causal discovery, and build a classifier that achieves state-of-the-art performance on finding the causal direction between pairs of random variables, given samples from their joint distribution. Second, we use our causal direction classifier to effectively distinguish between features of objects and features of their contexts in collections of static images. Our experiments demonstrate the existence of a relation between the direction of causality and the difference between objects and their contexts, and by the same token, the existence of observable signals that reveal the causal dispositions of objects. //Abstract//: This paper establishes the existence of observable foot- prints that reveal the “causal dispositions” of the object categories appearing in collections of images. We achieve this goal in two steps. First, we take a learning approach to observational causal discovery, and build a classifier that achieves state-of-the-art performance on finding the causal direction between pairs of random variables, given samples from their joint distribution. Second, we use our causal direction classifier to effectively distinguish between features of objects and features of their contexts in collections of static images. Our experiments demonstrate the existence of a relation between the direction of causality and the difference between objects and their contexts, and by the same token, the existence of observable signals that reveal the causal dispositions of objects.
  
-<box 99% green>+<box 99% orange>
 David Lopez-Paz, Robert Nishihara, Soumith Chintalah, Bernhard Schölkopf and Léon Bottou:  **Discovering Causal Signals in Images**,  //Proceedings of Computer Vision and Pattern Recognition (CVPR)//, IEEE, 2017. David Lopez-Paz, Robert Nishihara, Soumith Chintalah, Bernhard Schölkopf and Léon Bottou:  **Discovering Causal Signals in Images**,  //Proceedings of Computer Vision and Pattern Recognition (CVPR)//, IEEE, 2017.
  
papers/lopezpaz-2017.1498163723.txt.gz · Last modified: 2017/06/22 16:35 by leonb

Page Tools