Research map / Detection and segmentation / CNN features
Orthogonal Decomposition Network for Pixel-Wise Binary Classification
Chang Liu, Fang Wan, Wei Ke, Zhuowei Xiao, Yuan Yao, Xiaosong Zhang, Qixiang Ye
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 |
|---|---|---|---|
| add ODUs to SRN | SRN · SK-LARGE | F-measure: 0.655 -> 0.676 | Improved |
| add ODUs to SRN | SRN · BSDS500 | ODS: 0.782 -> 0.798 | Improved |
| add ODUs to SRN | SRN · MSRA-B | Fβ: 0.888 -> 0.899 | Improved |
| add ODUs to SRN | SRN · S-wave arrival time detection | sample proportion within deviation ≤0.20s: 0.722 -> 0.767 | Improved |
| use 3 × 3 decomposition patches instead of no decomposition (ablation) | OD-HED · SK-LARGE | F-measure: 0.489 -> 0.604 | Improved |
| increase decomposition patch size from 3 × 3 to 5 × 5 (ablation) | OD-HED · SK-LARGE | F-measure: 0.604 -> 0.606 | Improved |
| increase decomposition patch size from 5 × 5 to 7 × 7 (ablation) | OD-HED · SK-LARGE | F-measure: 0.606 -> 0.600 | Hurt |
| increase reconstruction filter size from 3 × 3 to 15 × 15 (ablation) | OD-HED · SK-LARGE | F-measure: 0.511 -> 0.620 | Improved |
| increase reconstruction filter size from 15 × 15 to 17 × 17 (ablation) | OD-HED · SK-LARGE | F-measure: 0.620 -> 0.619 | Hurt |
Closest papers by meaning
- RelationNet++: Bridging Visual Representations for Object Detection via Transformer Decoder (NeurIPS 2020 · similarity 0.83)
- Feature Pyramid Networks for Object Detection (CVPR 2017 · similarity 0.83)
- Deep Decoder: Concise Image Representations from Untrained Non-convolutional Networks (ICLR 2019 · similarity 0.82)
- Network Deconvolution (ICLR 2020 · similarity 0.82)
- An Adaptive Orthogonal Convolution Scheme for Efficient and Flexible CNN Architectures (ICML 2025 · similarity 0.82)
- FD2-Net: Frequency-Driven Feature Decomposition Network for Infrared-Visible Object Detection (AAAI 2025 · similarity 0.81)
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.
