Research map / Detection and segmentation / Weakly supervised detection and segmentation
Learning Transferrable Knowledge for Semantic Segmentation With Deep Convolutional Neural Network
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 |
|---|---|---|---|
| Transfer category-independent decoder knowledge using attention trained with source-category segmentation annotations | TransferNet · PASCAL VOC 2012 validation | mean IoU: 42.0 -> 52.1 | Helped |
| Transfer category-independent decoder knowledge using attention trained with source-category segmentation annotations | TransferNet · PASCAL VOC 2012 test | mean IoU: 40.6 -> 51.2 | Helped |
| Use ground-truth class labels instead of predicted labels for segmentation inference (ablation) | TransferNet · PASCAL VOC 2012 validation | mean IoU: 52.1 -> 54.3 | Helped |
| Add attention to the source-trained decoupled encoder-decoder transfer baseline (ablation) | DecoupledNet† · PASCAL VOC 2012 validation | mean IoU: 25.4 -> 52.1 | Helped |
| Replace attention-derived decoder input with class score maps (ablation) | TransferNet · PASCAL VOC 2012 validation | mean IoU: 52.1 -> 36.3 | Hurt |
| Use multiplicative feature-label interactions instead of additive interactions such as concatenation (ablation) | TransferNet attention model · PASCAL VOC 2012 | segmentation performance | Helped |
| Increase the number of source-domain segmentation annotations (ablation) | TransferNet · PASCAL VOC 2012 | segmentation quality | Helped |
Closest papers by meaning
- Combining Bottom-Up, Top-Down, and Smoothness Cues for Weakly Supervised Image Segmentation (CVPR 2017 · similarity 0.90)
- Transferable Semi-Supervised Semantic Segmentation (AAAI 2018 · similarity 0.90)
- Webly Supervised Semantic Segmentation (CVPR 2017 · similarity 0.89)
- L2G: A Simple Local-to-Global Knowledge Transfer Framework for Weakly Supervised Semantic Segmentation (CVPR 2022 · similarity 0.88)
- Weakly-Supervised Semantic Segmentation Network With Deep Seeded Region Growing (CVPR 2018 · similarity 0.88)
- Background-Aware Pooling and Noise-Aware Loss for Weakly-Supervised Semantic Segmentation (CVPR 2021 · similarity 0.87)
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.