End-to-end weakly-supervised semantic alignment

Ignacio Rocco (1) , Relja Arandjelovic (2) , Josef Sivic (1, 3)

1 WILLOW - Models of visual object recognition and scene understanding
2 DeepMind [London]
3 CIIRC - Czech Institute of Informatics, Robotics and Cybernetics [Prague]

We tackle the task of semantic alignment where the goal is to compute dense semantic correspondence aligning two images depicting objects of the same category. This is a challenging task due to large intra-class variation, changes in viewpoint and background clutter. We present the following three principal contributions. First, we develop a convo-lutional neural network architecture for semantic alignment that is trainable in an end-to-end manner from weak image-level supervision in the form of matching image pairs. The outcome is that parameters are learnt from rich appearance variation present in different but semantically related images without the need for tedious manual annotation of correspondences at training time. Second, the main component of this architecture is a differentiable soft inlier scoring module, inspired by the RANSAC inlier scoring procedure , that computes the quality of the alignment based on only geometrically consistent correspondences thereby reducing the effect of background clutter. Third, we demonstrate that the proposed approach achieves state-of-the-art performance on multiple standard benchmarks for semantic alignment.

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]

Ignacio Rocco, Relja Arandjelovic, Josef Sivic. End-to-end weakly-supervised semantic alignment. CVPR 2018 - IEEE Conference on Computer Vision and Pattern Recognition, Jun 2018, Salt Lake City, UT, United States. pp.1-9. ⟨hal-01859628⟩