Hypercorrelation Squeeze for Few-Shot Segmentation
This addresses the problem of segmenting objects with minimal annotated data for computer vision applications, representing a novel method for a known bottleneck.
The paper tackles few-shot semantic segmentation by proposing Hypercorrelation Squeeze Networks (HSNet), which uses multi-level feature correlation and efficient 4D convolutions to achieve significant performance improvements on benchmarks like PASCAL-5i, COCO-20i, and FSS-1000.
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.