Adaptive Prototype Learning and Allocation for Few-Shot Segmentation

By Gen Li, Varun Jampani, Laura Sevilla-Lara, Deqing Sun, Jonghyun Kim, Joongkyu Kim. 2021

502 citations recorded by the source corpus.

Prototype learning is extensively used for few-shot segmentation. Typically, a single prototype is obtained from the support feature by averaging the global object information. However, using one prototype to represent all the information may lead to ambiguities. In this paper, we propose two novel modules, named superpixel-guided clustering (SGC) and guided prototype allocation (GPA), for multiple prototype extraction and allocation. Specifically, SGC is a parameter-free and training-free approach, which extracts more representative prototypes by aggregating similar feature vectors, while GPA is able to select matched prototypes to provide more accurate guidance. By integrating the SGC and GPA together, we propose the Adaptive Superpixel-guided Network (ASGNet), which is a lightweight model and adapts to object scale and shape variation. In addition, our network can easily generalize to k-shot segmentation with substantial improvement and no additional computational cost. In particular, our evaluations on COCO demonstrate that ASGNet surpasses the state-of-the-art method by 5% in 5-shot segmentation.1

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

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

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Incremental Few-Shot Semantic Segmentation via Embedding Adaptive-Update and Hyper-class Representation (2022, background): “Few-shot semantic segmentation [21, 28, 40] addresses to segment a new category of images with few samples, decreasing the cost of expensive pixel-level annotations.”
Generalized Few-shot Semantic Segmentation (2020, background): “Besides, even if users have already known that there are N classes contained in the test image, FS-Seg models [3, 17, 23, 39, 55, 57, 58] may need to process NK additional manually selected support images/labels to make predictions over all possible classes for the test image.”
Learning What Not to Segment: A New Perspective on Few-Shot Segmentation (2022, methodology): “More recently, some relevant research abandoned the training process of heavy backbone networks in favor of building powerful blocks on the fixed ones to boost performance, such as CANet [66], PFENet [51], ASGNet [23], SAGNN [60], and MM-Net [58].”