Pyramidal Semantic Correspondence Networks
- 주제(키워드) Semantics , Computer architecture , Proposals , Strain , Feature extraction , Robustness , Microprocessors , Dense semantic correspondence , spatial pyramid model , coarse-to-fine inference
- 주제(기타) Computer Science, Artificial Intelligence; Engineering, Electrical & Electronic
- 설명문(일반) [Jeon, Sangryul; Sohn, Kwanghoon] Yonsei Univ, Sch Elect & Elect Engn, Seoul 03722, South Korea; [Kim, Seungryong] Korea Univ, Dept Comp Sci & Engn, Seoul 02841, South Korea; [Min, Dongbo] Ewha Womans Univ, Dept Comp Sci & Engn, Seoul 03760, South Korea
- 관리정보기술 faculty
- 등재 SCIE, SCOPUS
- OA유형 hybrid
- 발행기관 IEEE COMPUTER SOC
- 발행년도 2022
- 총서유형 Journal
- URI http://www.dcollection.net/handler/ewha/000000203082
- 본문언어 영어
- Published As https://doi.org/10.1109/TPAMI.2021.3123679
- PubMed https://pubmed.ncbi.nlm.nih.gov/34714738
초록/요약
This paper presents a deep architecture, called pyramidal semantic correspondence networks (PSCNet), that estimates locally-varying affine transformation fields across semantically similar images. To deal with large appearance and shape variations that commonly exist among different instances within the same object category, we leverage a pyramidal model where the affine transformation fields are progressively estimated in a coarse-to-fine manner so that the smoothness constraint is naturally imposed. Different from the previous methods which directly estimate global or local deformations, our method first starts to estimate the transformation from an entire image and then progressively increases the degree of freedom of the transformation by dividing coarse cell into finer ones. To this end, we propose two spatial pyramid models by dividing an image in a form of quad-tree rectangles or into multiple semantic elements of an object. Additionally, to overcome the limitation of insufficient training data, a novel weakly-supervised training scheme is introduced that generates progressively evolving supervisions through the spatial pyramid models by leveraging a correspondence consistency across image pairs. Extensive experimental results on various benchmarks including TSS, Proposal Flow-WILLOW, Proposal Flow-PASCAL, Caltech-101, and SPair-71k demonstrate that the proposed method outperforms the lastest methods for dense semantic correspondence.
more