Research map / Detection and segmentation / CNN features
Learning the Superpixel in a Non-Iterative and Lifelong Manner
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 FEM features with grid seed nodes instead of RIM's approach (ablation) | LNS-Net · BSDS500 | superpixel segmentation performance | Helped |
| Add the seed estimation layer (SEL) to generate seed nodes (ablation) | LNS-Net · BSDS500 | Boundary Recall | Helped |
| Add the seed estimation layer (SEL) to generate seed nodes (ablation) | LNS-Net · BSDS500 | ASA | Helped |
| Add the seed estimation layer (SEL) to generate seed nodes (ablation) | LNS-Net · BSDS500 | F-beta score | Helped |
| Add the gradient rescaling module (GRM) (ablation) | LNS-Net · BSDS500 | Boundary Recall | Helped |
| Add the gradient rescaling module (GRM) (ablation) | LNS-Net · BSDS500 | Boundary Precision | Helped |
| Add the gradient rescaling module (GRM) (ablation) | LNS-Net · BSDS500 | ASA | Helped |
| Add the gradient rescaling module (GRM) (ablation) | LNS-Net · BSDS500 | F-beta score | Helped |
| Use unsupervised contour maps rather than supervised-learned contour maps in GRM (ablation) | LNS-Net · BSDS500 | superpixel segmentation performance | No clear effect |
| Use LNS-Net instead of ERS | Superpixel segmentation · DRIVE | Boundary Recall | Hurt |
| Use LNS-Net instead of ERS | Superpixel segmentation · DRIVE | ASA | Helped |
| Use LNS-Net instead of competing methods | Superpixel segmentation · Duck DME | superpixel segmentation scores | Helped |
Closest papers by meaning
- Superpixel Segmentation With Fully Convolutional Networks (CVPR 2020 · similarity 0.89)
- Learning Invariant Inter-pixel Correlations for Superpixel Generation (AAAI 2024 · similarity 0.85)
- LSNet: See Large, Focus Small (CVPR 2025 · similarity 0.84)
- SCCS: Deep Neural Spectral Clustering for Self-Supervised Subcellular Structure Segmentation (AAAI 2025 · similarity 0.83)
- Hierarchical Histogram Threshold Segmentation - Auto-terminating High-detail Oversegmentation (CVPR 2024 · similarity 0.83)
- Segment Anything without Supervision (NeurIPS 2024 · similarity 0.83)
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.