Hypercorrelation Squeeze for Few-Shot Segmentation
- Title
- Hypercorrelation Squeeze for Few-Shot Segmentation
- Authors
- JU, HONG MIN; DAHYUN, KANG; CHO, MINSU
- Date Issued
- 2021-10-12
- Publisher
- IEEE / CVF
- Abstract
- 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-5i, COCO-20i, and FSS-1000 verify the efficacy of the proposed method.
- URI
- https://oasis.postech.ac.kr/handle/2014.oak/108185
- Article Type
- Conference
- Citation
- International Conference on Computer Vision, 2021-10-12
- Files in This Item:
- There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.