SimPropNet: Improved Similarity Propagation for Few-shot Image Segmentation

Gairola, Siddhartha; Hemani, Mayur; Chopra, Ayush; Krishnamurthy, Balaji

doi:10.48550/arxiv.2004.15014

Cited by 5 publications

(5 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…PANet makes full use of the knowledge of support images, and uses cosine distance for final segmentation. Gairola et al [ 29 ] proposed a novel similarity propagation network, which finds that the background region of different images from the same class have strong similarity, and uses this similarity to improve segmentation performance. Zhang et al [ 30 ] proposed a similarity guidance network (SG-One), which uses masked average pooling to extract foreground and background features of support images.…”

Section: Related Workmentioning

confidence: 99%

MCEENet: Multi-Scale Context Enhancement and Edge-Assisted Network for Few-Shot Semantic Segmentation

Zhang

et al. 2023

Sensors

View full text Add to dashboard Cite

Few-shot semantic segmentation has attracted much attention because it requires only a few labeled samples to achieve good segmentation performance. However, existing methods still suffer from insufficient contextual information and unsatisfactory edge segmentation results. To overcome these two issues, this paper proposes a multi-scale context enhancement and edge-assisted network (called MCEENet) for few-shot semantic segmentation. First, rich support and query image features were extracted, respectively, using two weight-shared feature extraction networks, each consisting of a ResNet and a Vision Transformer. Subsequently, a multi-scale context enhancement (MCE) module was proposed to fuse the features of ResNet and Vision Transformer, and further mine the contextual information of the image by using cross-scale feature fusion and multi-scale dilated convolutions. Furthermore, we designed an Edge-Assisted Segmentation (EAS) module, which fuses the shallow ResNet features of the query image and the edge features computed by the Sobel operator to assist in the final segmentation task. We experimented on the PASCAL-5i dataset to demonstrate the effectiveness of MCEENet; the results of the 1-shot setting and 5-shot setting on the PASCAL-5i dataset are 63.5% and 64.7%, which surpasses the state-of-the-art results by 1.4% and 0.6%, respectively.

show abstract

Section: Related Workmentioning

confidence: 99%

MCEENet: Multi-Scale Context Enhancement and Edge-Assisted Network for Few-Shot Semantic Segmentation

Zhang

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Few-shot semantic segmentation [6,8,27,21,23,5] aims to give a dense segmentation prediction for new class query images with only a few labeled support images. CANet [34] proposed Dense Comparison Module (DCM) and Iterative Optimization Module (IOM) to give a dense prediction and iteratively refine the prediction.…”

Section: Few-shot Semantic Segmentationmentioning

confidence: 99%

Learning Meta-class Memory for Few-Shot Semantic Segmentation

Shi

Lin

et al. 2021

Preprint

View full text Add to dashboard Cite

Currently, the state-of-the-art methods treat few-shot semantic segmentation task as a conditional foregroundbackground segmentation problem, assuming each class is independent. In this paper, we introduce the concept of meta-class, which is the meta information (e.g. certain middle-level features) shareable among all classes. To explicitly learn meta-class representations in few-shot segmentation task, we propose a novel Meta-class Memory based few-shot segmentation method (MM-Net), where we introduce a set of learnable memory embeddings to memorize the meta-class information during the base class training and transfer to novel classes during the inference stage. Moreover, for the k-shot scenario, we propose a novel image quality measurement module to select images from the set of support images. A high-quality class prototype could be obtained with the weighted sum of support image features based on the quality measure. Experiments on both PASCAL-5 i and COCO dataset shows that our proposed method is able to achieve state-of-the-art results in both 1shot and 5-shot settings. Particularly, our proposed MM-Net achieves 37.5% mIoU on the COCO dataset in 1-shot setting, which is 5.1% higher than the previous state-of-theart.

show abstract

“…Yang et al [12] exploited latent classes from the background to enhance features. Gairola et al [13] and Yang et al [14] calculated the background correlation map as an important auxiliary reference for segmentation. But these methods do not directly exploit the latent classes in the background, our method makes full use of the background through multi-class pseudo-labels and false-positive entropy loss.…”

Section: Introductionmentioning

confidence: 99%

Prototype Queue Learning for Multi-Class Few-Shot Semantic Segmentation

Wang

Jiang

Yuan

2022

2022 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

Few-shot semantic segmentation aims to undertake the segmentation task of novel classes with only a few annotated images. However, most existing methods tend to segment the foreground and background in the image, which limits practical application. In this paper, we present a Prototype Queue Network, which performs few-shot segmentation on multiclass in the images by aggregating binary classes into multiple classes. A prototype queue learning module is proposed to achieve multi-class segmentation by mining the relationship among features of different classes with queue and pseudo labels. In addition, a background latent class distribution refinement module is proposed to prevent the latent novel class in the background from being incorrectly predicted, which refines the boundary among different classes. Furthermore, we propose a two-steps segmentation module to optimize the process of extracting feature representation by adding progressive constraints, which can further improve the accuracy of segmentation. Experiments on the UDD and Vaihingen datasets demonstrate that our method achieves state-of-the-art performance.

show abstract

SimPropNet: Improved Similarity Propagation for Few-shot Image Segmentation

Cited by 5 publications

References 0 publications

MCEENet: Multi-Scale Context Enhancement and Edge-Assisted Network for Few-Shot Semantic Segmentation

MCEENet: Multi-Scale Context Enhancement and Edge-Assisted Network for Few-Shot Semantic Segmentation

Learning Meta-class Memory for Few-Shot Semantic Segmentation

Prototype Queue Learning for Multi-Class Few-Shot Semantic Segmentation

Contact Info

Product

Resources

About