Hypercorrelation Squeeze for Few-Shot Segmenation

By Juhong Min, Dahyun Kang, Minsu Cho. 2021

435 citations recorded by the source corpus.

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.

Subfields: Computer Vision and Pattern Recognition, Meta & Continual Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Meta & Continual Learning

Citations in the corpus

Language-driven Semantic Segmentation (2022, methodology): “…et al., 2017; Rakelly et al., 2018; Siam et al., 2019; Wang et al., 2019; Zhang et al., 2019; Nguyen & Todorovic, 2019; Liu et al., 2020b; Wang et al., 2020; Tian et al., 2020; Boudiaf et al., 2021; Min et al., 2021) offer ways to learn to segment novel classes based on only a few labeled images.”
Personalize Segment Anything Model with One Shot (2023, result): “For models (Min et al., 2021; Hong et al., 2022) with in-domain training, our approach can achieve higher scores than HSNet.”
Generalized Few-shot Semantic Segmentation (2020, background): “It is worth noting that some recently proposed advanced frameworks, e.g ., RePRI [3] and HSNet [23], are not practical to be applied to the setting of GFS-Seg because their inference processes require independent reasoning with the full support feature maps, instead of the prototypical feature vecto”
A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities (2022, neutral): “6 HSNet [258] ICCV’21 ResNet-50 Metric ✓ ✓ ✓ 66.”
Novel Class Discovery in Semantic Segmentation (2021, methodology): “Following few-shot semantic segmentation [18, 23], we split the base and novel classes as PASCAL-5 dataset [27].”
Image Segmentation Using Text and Image Prompts (2021, methodology): “Similarly, HSNet [55] processes correlated activations of query and support image using 4Dconvolutions at multiple levels.”
Few-Shot Segmentation via Cycle-Consistent Transformer (2021, background): “Recently, some concurrent works propose to learn dense matching through Hypercorrelation Squeeze Networks [22] or mining latent classes [42] from the background region.”