Research map / Detection and segmentation / CNN features
Laplacian Pyramid Reconstruction and Refinement for Semantic Segmentation
Golnaz Ghiasi, Charless C. Fowlkes
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 |
|---|---|---|---|
| replace upsampling of class scores with learned-basis reconstruction (10 bases) | FCN-32s · PASCAL VOC val (w/o scale aug) | mean IoU: 59.4% -> 64.1% | Improved |
| compare LRR 32x reconstruction against FCN-8s with skip fusion | FCN-8s · PASCAL VOC val (w/o scale aug) | mean IoU: 62.7% -> 64.1% | Improved |
| add multi-scale training augmentation (ablation) | LRR 32x · PASCAL VOC val | mean IoU: 64.07% -> 66.81% | Improved |
| add dilation and erosion losses to the 32x branch (ablation) | LRR-4x · PASCAL VOC val (32x branch) | mean IoU: 71.2% -> 72.9% | Improved |
| add dilation and erosion losses to the 32x branch (ablation) | LRR-4x · PASCAL VOC val (multi-scale) | mean IoU: 75.0% -> 76.6 | Improved |
| add multiplicative boundary masking to high-resolution branches (ablation) | LRR-4x · PASCAL VOC val | mean IoU: about 1% | Improved |
| add the 4x layer without boundary masking (ablation) | LRR fusion · PASCAL VOC val | mean IoU | No clear effect |
| fuse predictions at multiple test scales (ablation) | LRR-4x · PASCAL VOC val | mean IoU: between 1.1% to 2.5% | Improved |
| add fully connected CRF post-processing (ablation) | LRR-4x · PASCAL VOC val | mean IoU: between 0.9% to 1.4% | Improved |
| pretrain on MS COCO in addition to VOC | LRR-4x · PASCAL VOC 2011 val | mean IoU: 74.6% -> 77.5% | Improved |
| use more than 10 basis functions in reconstruction (ablation) | LRR reconstruction layer · PASCAL VOC val | mean IoU | No clear effect |
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 0.89)
- Full-Resolution Residual Networks for Semantic Segmentation in Street Scenes (CVPR 2017 · similarity 0.87)
- Decoders Matter for Semantic Segmentation: Data-Dependent Decoding Enables Flexible Feature Aggregation (CVPR 2019 · similarity 0.87)
- Revisiting Dilated Convolution: A Simple Approach for Weakly- and Semi-Supervised Semantic Segmentation (CVPR 2018 · similarity 0.87)
- Complex Wavelet Mutual Information Loss: A Multi-Scale Loss Function for Semantic Segmentation (ICML 2025 · 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.
