FGN: Fully Guided Network for Few-Shot Instance Segmentation

@article{Fan2020FGNFG,
  title={FGN: Fully Guided Network for Few-Shot Instance Segmentation},
  author={Zhibo Fan and Jin-Gang Yu and Zhihao Liang and Jiarong Ou and Changxin Gao and Guisong Xia and Yuanqing Li},
  journal={2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2020},
  pages={9169-9178}
}
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… Expand
Learning Meta-class Memory for Few-Shot Semantic Segmentation
  • Zhonghua Wu, Xiangxi Shi, Guosheng lin, Jianfei Cai
  • Computer Science
  • ArXiv
  • 2021
TLDR
This paper proposes a novel Meta-class Memory based few-shot segmentation method (MM-Net), where a set of learnable memory embeddings are introduced to memorize the meta-class information during the base class training and transfer to novel classes during the inference stage. Expand
Incremental Few-Shot Instance Segmentation
TLDR
The first incremental approach to few-shot instance segmentation: iMTFA is presented, which learns discriminative embeddings for object instances that are merged into class representatives that allows to add new classes without the need for further training or access to previous training data. Expand
FAPIS: A Few-shot Anchor-free Part-based Instance Segmenter
TLDR
A new few-shot anchor-free part-based instance segmenter (FAPIS) is specified and evaluated in explicit modeling of latent object parts shared across training object classes, which is expected to facilitate few- shot learning on new classes in testing. Expand
DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detection
Few-shot object detection, which aims at detecting novel objects rapidly from extremely few annotated examples of previously unseen classes, has attracted significant research interest in theExpand
Attentional Prototype Inference for Few-Shot Semantic Segmentation
TLDR
This work proposes attentional prototype inference (API), a probabilistic latent variable framework for few-shot semantic segmentation, that is formulated as a variational Bayesian inference problem, which is established by amortized inference networks. Expand
Generalized Few-Shot Object Detection without Forgetting
TLDR
The approach has demonstrated that the long desired neverforgetting learner is available in object detection and significantly outperforms state-ofthe-art methods on overall performance among all settings as it can achieve competitive results on few-shot classes and does not degrade the base class performance at all. Expand
One-Shot Shape-Based Amodal-to-Modal Instance Segmentation
TLDR
OSSIS is proposed, a single-stage One-Shot Shape-based Instance Segmentation algorithm that produces the target object modal segmentation mask in a depth image of a scene based only on a binary shape mask of thetarget object. Expand
Learning to Better Segment Objects from Unseen Classes with Unlabeled Videos
TLDR
This paper introduces a Bayesian method that is specifically designed to automatically create a high-quality training set which significantly boosts the performance of segmenting objects of unseen classes and could open the door for open-world instance segmentation using abundant Internet videos. Expand
ODIP: Towards Automatic Adaptation for Object Detection by Interactive Perception
TLDR
A novel object detector based on interactive perception (ODIP), which can be adapted to novel domains in an automated manner and outperforms both the generic object detector and state-of-the-art few-shot object detector fine-tuned in traditional manners. Expand
VideoClick: Video Object Segmentation with a Single Click
TLDR
This paper proposes a bottom up approach where given a single click for each object in a video, the segmentation masks of these objects in the full video are obtained and this approach outperforms all the baselines in this challenging setting. Expand
...
1
2
...

References

SHOWING 1-10 OF 33 REFERENCES
SG-One: Similarity Guidance Network for One-Shot Semantic Segmentation
TLDR
This article proposes a simple yet effective similarity guidance network to tackle the one-shot (SG-One) segmentation problem, aiming at predicting the segmentation mask of a query image with the reference to one densely labeled support image of the same category. Expand
Meta R-CNN: Towards General Solver for Instance-Level Low-Shot Learning
TLDR
This work extends Faster /Mask R-CNN by proposing meta-learning over RoI (Region-of-Interest) features instead of a full image feature, and introduces a Predictor-head Remodeling Network (PRN) that shares its main backbone with Faster / Mask R- CNN. Expand
End-to-End Instance Segmentation with Recurrent Attention
  • Mengye Ren, R. Zemel
  • Mathematics, Computer Science
  • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2017
TLDR
An end-to-end recurrent neural network (RNN) architecture with an attention mechanism to model a human-like counting process, and produce detailed instance segmentations is proposed. Expand
One-Shot Instance Segmentation
TLDR
Siamese Mask R-CNN is extended by a Siamese backbone encoding both reference image and scene, allowing it to target detection and segmentation towards the reference category. Expand
Proposal-Free Network for Instance-Level Object Segmentation
TLDR
A Proposal-Free Network (PFN) is proposed to address the instance-level object segmentation problem, which outputs the numbers of instances of different categories and the pixel-level information on i) the coordinates of the instance bounding box each pixel belongs to, and ii) the confidences ofDifferent categories for each pixel, based on pixel-to-pixel deep convolutional neural network. Expand
RepMet: Representative-Based Metric Learning for Classification and Few-Shot Object Detection
TLDR
This work proposes a new method for DML that simultaneously learns the backbone network parameters, the embedding space, and the multi-modal distribution of each of the training categories in that space, in a single end-to-end training process. Expand
Mask Scoring R-CNN
TLDR
This paper proposes Mask Scoring R-CNN which contains a network block to learn the quality of the predicted instance masks and calibrates the misalignment between mask quality and mask score, and improves instance segmentation performance by prioritizing more accurate mask predictions during COCO AP evaluation. Expand
Hybrid Task Cascade for Instance Segmentation
TLDR
This work proposes a new framework, Hybrid Task Cascade (HTC), which differs in two important aspects: (1) instead of performing cascaded refinement on these two tasks separately, it interweaves them for a joint multi-stage processing; (2) it adopts a fully convolutional branch to provide spatial context, which can help distinguishing hard foreground from cluttered background. Expand
Few-Shot Object Detection via Feature Reweighting
TLDR
This work develops a few-shot object detector that can learn to detect novel objects from only a few annotated examples, using a meta feature learner and a reweighting module within a one-stage detection architecture. Expand
Mask R-CNN
TLDR
This work presents a conceptually simple, flexible, and general framework for object instance segmentation that outperforms all existing, single-model entries on every task, including the COCO 2016 challenge winners. Expand
...
1
2
3
4
...