Unsupervised Image Matching and Object Discovery as Optimization

CVPR 2019  ·  Huy V. Vo, Francis Bach, Minsu Cho, Kai Han, Yann Lecun, Patrick Perez, Jean Ponce ·

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.

PDF Abstract CVPR 2019 PDF CVPR 2019 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Single-object colocalization Object Discovery OSD CorLoc 85.8 # 2
Compare
Single-object discovery Object Discovery OSD CorLoc 83 # 2
Compare
Single-object discovery VOC_6x2 OSD CorLoc 60.2 # 2
Compare
Single-object colocalization VOC_6x2 OSD CorLoc 69.4 # 2
Compare
Single-object colocalization VOC_all OSD CorLoc 39.2 # 2
Compare
Single-object discovery VOC_all OSD CorLoc 39.8 # 3
Compare

Methods
Add Remove

No methods listed for this paper. Add relevant methods here
Contact us on: hello@paperswithcode.com . Papers With Code is a free resource with all data licensed under CC-BY-SA.
Terms Data policy Cookies policy