FCSS: Fully Convolutional Self-Similarity for Dense Semantic Correspondence

Citations Over TimeTop 10% of 2017 papers

Abstract

We present a descriptor, called fully convolutional self-similarity (FCSS), for dense semantic correspondence. To robustly match points among different instances within the same object class, we formulate FCSS using local self-similarity (LSS) within a fully convolutional network. In contrast to existing CNN-based descriptors, FCSS is inherently insensitive to intra-class appearance variations because of its LSS-based structure, while maintaining the precise localization ability of deep neural networks. The sampling patterns of local structure and the self-similarity measure are jointly learned within the proposed network in an end-to-end and multi-scale manner. As training data for semantic correspondence is rather limited, we propose to leverage object candidate priors provided in existing image datasets and also correspondence consistency between object pairs to enable weakly-supervised learning. Experiments demonstrate that FCSS outperforms conventional handcrafted descriptors and CNN-based descriptors on various benchmarks.

Related Papers

• → An Adaptable Real-Time Object Detection for Traffic Surveillance using R-CNN over CNN with Improved Accuracy(2022)12 cited
• → Convolutional Neural Network for Automated Analyzing of Medical Images(2020)3 cited
• → Ocular Disease Detection Using Convolutional Neural Networks(2023)1 cited
• → SEGMENTATION OF MEDICAL IMAGES BY CONVOLUTIONAL NEURAL NETWORKS(2022)1 cited
• → Convolutional Neural Network (CNN) Applied to the Risk Analysis of Accidents in Vessels Navigating the Amazon Rivers(2023)