Back to Search Start Over

Joint Learning of Feature Extraction and Cost Aggregation for Semantic Correspondence

Authors :
Kim, Jiwon
Min, Youngjo
Kim, Mira
Kim, Seungryong
Source :
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2022
Publication Year :
2022

Abstract

Establishing dense correspondences across semantically similar images is one of the challenging tasks due to the significant intra-class variations and background clutters. To solve these problems, numerous methods have been proposed, focused on learning feature extractor or cost aggregation independently, which yields sub-optimal performance. In this paper, we propose a novel framework for jointly learning feature extraction and cost aggregation for semantic correspondence. By exploiting the pseudo labels from each module, the networks consisting of feature extraction and cost aggregation modules are simultaneously learned in a boosting fashion. Moreover, to ignore unreliable pseudo labels, we present a confidence-aware contrastive loss function for learning the networks in a weakly-supervised manner. We demonstrate our competitive results on standard benchmarks for semantic correspondence.

Details

Database :
arXiv
Journal :
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2022
Publication Type :
Report
Accession number :
edsarx.2204.02164
Document Type :
Working Paper