Research map / Detection and segmentation / Open-set and few-shot detection
Pyramid Graph Networks With Connection Attentions for Region-Based One-Shot Semantic Segmentation
Chi Zhang, Guosheng Lin, Fayao Liu, Jiushuang Guo, Qingyao Wu, Rui Yao
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use ResNet-50 backbone instead of VGG-16 (ablation) | PGNet-Dot · PASCAL-5i ablation | mean IoU: 57.2 -> 59.4 | Improved |
| use dot-product pair-wise function instead of linear transformation (ablation) | PGNet · PASCAL-5i ablation | mean IoU: 58.1 -> 59.4 | Improved |
| add adaptive average pooling on query feature maps vs baseline ensemble (ablation) | PGNet · PASCAL-5i ablation | mean IoU: 57.5 -> 59.4 | Improved |
| replace adaptive avg pooling on query with dilated convolution (ablation) | PGNet · PASCAL-5i ablation | mean IoU: 59.4 -> 57.7 | Hurt |
| apply adaptive avg pooling on support instead of query (ablation) | PGNet · PASCAL-5i ablation | mean IoU: 59.4 -> 57.6 | Hurt |
| apply adaptive max pooling on query instead of average (ablation) | PGNet · PASCAL-5i ablation | mean IoU: 59.4 -> 57.6 | Hurt |
| use graph attention reasoning instead of global vector (Mask-Feature) (ablation) | PGNet · PASCAL-5i ablation | mean IoU: 56.7 -> 59.4 | Improved |
| use graph attention reasoning instead of global vector (Mask-RGB) (ablation) | PGNet · PASCAL-5i ablation | mean IoU: 54.7 -> 59.4 | Improved |
| branch ensemble of Mask-RGB baseline (ablation) | PGNet-Mask-RGB · PASCAL-5i ablation | mean IoU: 54.7 -> 54.8 | No clear effect |
| branch ensemble of Mask-Feature baseline (ablation) | PGNet-Mask-Feature · PASCAL-5i ablation | mean IoU: 56.7 -> 57.1 | Improved |
| add multi-scale test on query images (ablation) | PGNet-Dot · PASCAL-5i ablation | mean IoU: 59.4 -> 61.2 | Improved |
| add multi-scale test on support images (ablation) | PGNet-Dot · PASCAL-5i ablation | mean IoU: 59.4 -> 59.5 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- CANet — CANet: Class-Agnostic Segmentation Networks With Iterative Refinement and Attentive Few-Shot Learning (CVPR 2019) · better on 4 of 4 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Spatial Pyramid Based Graph Reasoning for Semantic Segmentation (CVPR 2020 · similarity 0.91)
- DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs (TPAMI 2017 · similarity 0.88)
- Segmenting Objects From Relational Visual Data (TPAMI 2021 · similarity 0.88)
- Scale-Aware Graph Neural Network for Few-Shot Semantic Segmentation (CVPR 2021 · similarity 0.87)
- Bridge the Points: Graph-based Few-shot Segment Anything Semantically (NeurIPS 2024 · similarity 0.86)
- Unlocking the Potential of Pre-trained Vision Transformers for Few-Shot Semantic Segmentation through Relationship Descriptors (CVPR 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
