Timezone: »
Many machine learning tasks require finding per-part correspondences between objects. In this work we focus on low-level correspondences --- a highly ambiguous matching problem. We propose to use a hierarchical semantic representation of the objects, coming from a convolutional neural network, to solve this ambiguity. Training it for low-level correspondence prediction directly might not be an option in some domains where the ground-truth correspondences are hard to obtain. We show how transfer from recognition can be used to avoid such training. Our idea is to mark parts as ``matching'' if their features are close to each other at all the levels of convolutional feature hierarchy (neural paths). Although the overall number of such paths is exponential in the number of layers, we propose a polynomial algorithm for aggregating all of them in a single backward pass. The empirical validation is done on the task of stereo correspondence and demonstrates that we achieve competitive results among the methods which do not use labeled target domain data.
Author Information
Nikolay Savinov (ETH Zurich)
Lubor Ladicky (ETH Zurich)
Marc Pollefeys (ETH Zurich)
More from the Same Authors
-
2021 Oral: Shape As Points: A Differentiable Poisson Solver »
Songyou Peng · Chiyu Jiang · Yiyi Liao · Michael Niemeyer · Marc Pollefeys · Andreas Geiger -
2021 Poster: Shape As Points: A Differentiable Poisson Solver »
Songyou Peng · Chiyu Jiang · Yiyi Liao · Michael Niemeyer · Marc Pollefeys · Andreas Geiger -
2021 Poster: Shape from Blur: Recovering Textured 3D Shape and Motion of Fast Moving Objects »
Denys Rozumnyi · Martin R. Oswald · Vittorio Ferrari · Marc Pollefeys -
2019 Poster: Reflection Separation using a Pair of Unpolarized and Polarized Images »
Youwei Lyu · Zhaopeng Cui · Si Li · Marc Pollefeys · Boxin Shi -
2019 Spotlight: Reflection Separation using a Pair of Unpolarized and Polarized Images »
Youwei Lyu · Zhaopeng Cui · Si Li · Marc Pollefeys · Boxin Shi -
2012 Poster: Globally Convergent Dual MAP LP Relaxation Solvers using Fenchel-Young Margins »
Alex Schwing · Tamir Hazan · Marc Pollefeys · Raquel Urtasun -
2010 Poster: Gated Softmax Classification »
Roland Memisevic · Christopher Zach · Geoffrey E Hinton · Marc Pollefeys