Learning Semantic Correspondence Exploiting an Object-level Prior

Junghyup Lee 1 Dohyung Kim 1 Wonkyung Lee 1 Jean Ponce 2 Bumsub Ham 1
2 WILLOW - Models of visual object recognition and scene understanding
Inria de Paris, DI-ENS - Département d'informatique de l'École normale supérieure
Abstract : We address the problem of semantic correspondence, that is, establishing a dense flow field between images depicting different instances of the same object or scene category. We propose to use images annotated with binary foreground masks and subjected to synthetic geometric deformations to train a convolutional neural network (CNN) for this task. Using these masks as part of the supervisory signal provides an object-level prior for the semantic correspondence task and offers a good compromise between semantic flow methods, where the amount of training data is limited by the cost of manually selecting point correspondences, and semantic alignment ones, where the regression of a single global geometric transformation between images may be sensitive to image-specific details such as background clutter. We propose a new CNN architecture, dubbed SFNet, which implements this idea. It leverages a new and differentiable version of the argmax function for end-to-end training, with a loss that combines mask and flow consistency with smoothness terms. Experimental results demonstrate the effectiveness of our approach, which significantly outperforms the state of the art on standard benchmarks.
Document type :
Preprints, Working Papers, ...
Complete list of metadatas

Contributor : Dohyung Kim <>
Submitted on : Tuesday, January 14, 2020 - 12:40:00 PM
Last modification on : Wednesday, January 15, 2020 - 1:43:41 AM


Files produced by the author(s)


  • HAL Id : hal-02433226, version 2



Junghyup Lee, Dohyung Kim, Wonkyung Lee, Jean Ponce, Bumsub Ham. Learning Semantic Correspondence Exploiting an Object-level Prior. 2020. ⟨hal-02433226v2⟩



Record views


Files downloads