Learning Semantic Correspondence Exploiting an Object-level Prior

TL;DR

This paper introduces SFNet, a CNN that uses object masks and synthetic deformations to improve dense semantic correspondence between images, outperforming previous methods.

Contribution

The paper proposes a novel CNN architecture, SFNet, incorporating an object-level prior and a differentiable argmax for end-to-end training in semantic correspondence.

Findings

SFNet significantly outperforms state-of-the-art methods on benchmark datasets.

Using object masks as supervision improves correspondence accuracy.

The differentiable argmax enables effective end-to-end training of the network.

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.