FGN: Fully Guided Network for Few-Shot Instance Segmentation

By Zhibo Fan, Jin-Gang Yu, Zhihao Liang, Jiarong Ou, Changxin Gao, Guisong Xia, Yuanqing Li. 2020

83 citations recorded by the source corpus.

Few-shot instance segmentation (FSIS) conjoins the few-shot learning paradigm with general instance segmentation, which provides a possible way of tackling instance segmentation in the lack of abundant labeled data for training. This paper presents a Fully Guided Network (FGN) for few-shot instance segmentation. FGN perceives FSIS as a guided model where a so-called support set is encoded and utilized to guide the predictions of a base instance segmentation network (i.e., Mask R-CNN), critical to which is the guidance mechanism. In this view, FGN introduces different guidance mechanisms into the various key components in Mask R-CNN, including Attention-Guided RPN, Relation-Guided Detector, and Attention-Guided FCN, in order to make full use of the guidance effect from the support set and adapt better to the inter-class generalization. Experiments on public datasets demonstrate that our proposed FGN can outperform the state-of-the-art methods.

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

1. Li Jiang
2. Hengshuang Zhao
3. Yang Xiao
4. Zhuotao Tian
5. Vincent Lepetit
6. Jiaya Jia
7. Xi Qiu
8. Juhong Min

In Computer Vision and Pattern Recognition

1. Luc Van Gool
2. Jiaya Jia
3. Ming-Hsuan Yang
4. Jitendra Malik
5. Trevor Darrell
6. Dacheng Tao
7. Xiaogang Wang
8. Cordelia Schmid

Citations in the corpus

• Hypercorrelation Squeeze for Few-Shot Segmenation (2021, background): “However, given only a few annotated training examples, the problem of poor generalization ability of the deep networks is yet the primary concern that many few-shot segmentation methods [10, 12, 13, 19, 33, 36, 37, 46, 54, 61, 63, 69, 70, 74, 75, 80, 83, 86, 87, 89] struggle to address.”
• A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities (2022, unknown): “2 FGN [266] CVPR’20 ResNet-101 Meta ✓ ✓ ✓ 16.”
• Generalized Few-shot Semantic Segmentation (2020, background): “Few-Shot Segmentation (FSSeg) places semantic segmentation in the few-shot scenario [2,8,11,15,18,20,21,24,27,28,33,34,38,41,48,51,52,57, 61, 62, 66, 67], where dense pixel labeling is performed on new classes with only a few support samples.”
• Few-Shot Object Detection and Viewpoint Estimation for Objects in the Wild (2020, methodology): “This reweighting module computes a feature similarity between query images and support classes, which has also been demonstrated to be useful in few-shot instance segmentation [4] and few-shot image classification [5].”
• DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detection (2021, background): “Since previous detectors usually require a large amount of annotated data, few-shot detection has attracted more and more interest recently [2, 10, 12, 28, 31, 45, 47, 52, 54].”