Unsupervised Image Matching and Object Discovery as Optimization
This work addresses the need for reducing human annotation efforts in computer vision, though it appears incremental as it builds directly on prior research.
The paper tackles the problem of unsupervised object discovery and matching in image collections by reformulating an existing approach as an optimization problem, with experiments on benchmarks demonstrating its merit.
Learning with complete or partial supervision is powerful but relies on ever-growing human annotation efforts. As a way to mitigate this serious problem, as well as to serve specific applications, unsupervised learning has emerged as an important field of research. In computer vision, unsupervised learning comes in various guises. We focus here on the unsupervised discovery and matching of object categories among images in a collection, following the work of Cho et al. 2015. We show that the original approach can be reformulated and solved as a proper optimization problem. Experiments on several benchmarks establish the merit of our approach.