Journal
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
Volume -, Issue -, Pages 6921-6932Publisher
IEEE
DOI: 10.1109/ICCV48922.2021.00686
Keywords
-
Funding
- Samsung Advanced Institute of Technology (SAIT)
- NRF grant [NRF-2017R1E1A1A01077999]
- IITP grant - Ministry of Science and ICT, Korea [2019-0-01906]
- Institute for Information & Communication Technology Planning & Evaluation (IITP), Republic of Korea [2019-0-01906-003] Funding Source: Korea Institute of Science & Technology Information (KISTI), National Science & Technology Information Service (NTIS)
Ask authors/readers for more resources
The paper introduces a model called HSNet, which utilizes multi-level feature correlation and efficient 4D convolutions to achieve semantic segmentation with few-shot learning.
Few-shot semantic segmentation aims at learning to segment a target object from a query image using only a few annotated support images of the target class. This challenging task requires to understand diverse levels of visual cues and analyze fine-grained correspondence relations between the query and the support images. To address the problem, we propose Hypercorrelation Squeeze Networks (HSNet) that leverages multi-level feature correlation and efficient 4D convolutions. It extracts diverse features from different levels of intermediate convolutional layers and constructs a collection of 4D correlation tensors, i.e., hypercorrelations. Using efficient center-pivot 4D convolutions in a pyramidal architecture, the method gradually squeezes high-level semantic and low-level geometric cues of the hypercorrelation into precise segmentation masks in coarse-to-fine manner. The significant performance improvements on standard few-shot segmentation benchmarks of PASCAL-5(i), COCO-20(i), and FSS-1000 verify the efficacy of the proposed method.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available