• Corpus ID: 220347608

Few-Shot Semantic Segmentation Augmented with Image-Level Weak Annotations

@article{Lei2020FewShotSS,
  title={Few-Shot Semantic Segmentation Augmented with Image-Level Weak Annotations},
  author={Shuo Lei and Xuchao Zhang and Jianfeng He and Fanglan Chen and Chang-Tien Lu},
  journal={ArXiv},
  year={2020},
  volume={abs/2007.01496}
}
Despite the great progress made by deep neural networks in the semantic segmentation task, traditional neural network-based methods typically suffer from a shortage of large amounts of pixel-level annotations. Recent progress in few-shot semantic segmentation tackles the issue by utilizing only a few pixel-level annotated examples. However, these few-shot approaches cannot easily be applied to utilize image-level weak annotations, which can easily be obtained and considerably improve… 

Figures and Tables from this paper

Self-Guided and Cross-Guided Learning for Few-Shot Segmentation
TLDR
A cross-guided module for multiple shot segmentation, where the final mask is fused using predictions from multiple annotated samples with high-quality support vectors contributing more and vice versa, which improves the final prediction in the inference stage without re-training.

References

SHOWING 1-10 OF 41 REFERENCES
Part-aware Prototype Network for Few-shot Semantic Segmentation
TLDR
A novel few-shot semantic segmentation framework based on the prototype representation, capable of capturing diverse and fine-grained object features, and a novel graph neural network model to generate and enhance the proposed part-aware prototypes based on labeled and unlabeled images.
PANet: Few-Shot Image Semantic Segmentation With Prototype Alignment
TLDR
This paper tackles the challenging few-shot segmentation problem from a metric learning perspective and presents PANet, a novel prototype alignment network to better utilize the information of the support set to better generalize to unseen object categories.
Few-Shot Semantic Segmentation with Prototype Learning
TLDR
A generalized framework for few-shot semantic segmentation with an alternative training scheme based on prototype learning and metric learning is proposed, which outperforms the baselines by a large margin and shows comparable performance for 1-way few- shot semantic segmentsation on PASCAL VOC 2012 dataset.
Microsoft COCO: Common Objects in Context
We present a new dataset with the goal of advancing the state-of-the-art in object recognition by placing the question of object recognition in the context of the broader question of scene
Learning to Compare: Relation Network for Few-Shot Learning
TLDR
A conceptually simple, flexible, and general framework for few-shot learning, where a classifier must learn to recognise new classes given only few examples from each, which is easily extended to zero- shot learning.
Semi-Supervised Semantic Segmentation With High- and Low-Level Consistency
TLDR
This work proposes an approach for semi-supervised semantic segmentation that learns from limited pixel-wise annotated samples while exploiting additional annotation-free images, and achieves significant improvement over existing methods, especially when trained with very few labeled samples.
Prototype Mixture Models for Few-shot Semantic Segmentation
TLDR
Proposed prototype mixture models (PMMs), which correlate diverse image regions with multiple prototypes to enforce the prototype-based semantic representation, incorporate rich channel-wised and spatial semantics from limited support images.
Prototype Refinement Network for Few-Shot Segmentation
TLDR
A Prototype Refinement Network (PRNet) is proposed which fuses support prototypes with query prototypes, incorporating the knowledge from both sides and is effective in prototype refinement without importing extra learnable parameters.
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.
...
1
2
3
4
5
...