Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
Uncertainty-Aware Learning for Zero-Shot Semantic Segmentation
Ping Hu, Stan Sclaroff, Kate Saenko
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 |
|---|---|---|---|
| add uncertainty-aware losses (image-level and pixel-level) (ablation) | ZSS baseline · Pascal-Context, 30 unseen | unseen mIoU: 13.9 -> 18.6 | Improved |
| add uncertainty-aware losses (image-level and pixel-level) (ablation) | ZSS baseline · Pascal-Context, 156 unseen | unseen mIoU: 11.7 -> 13.3 | Improved |
| add uncertainty-aware losses (image-level and pixel-level) (ablation) | ZSS baseline · ADE20K, 75 unseen | unseen mIoU: 13.5 -> 15.2 | Improved |
| add a single uncertainty-aware loss branch (image-level or pixel-level alone) (ablation) | ZSS baseline · Pascal-Context 156 / ADE20K 75 unseen | unseen mIoU: -0.2 to +2.2 | Mixed |
| add uncertainty-aware learning | ZSS baseline · Pascal-Context, 10 unseen | unseen mIoU: 27.9 -> 35.4 | Improved |
| add uncertainty-aware learning | ZSS baseline · ADE20K, 25 unseen | overall mIoU: 32.0 -> 31.9 | No clear effect |
| add uncertainty-aware learning | ZSS baseline · ADE20K, 50 unseen | unseen mIoU: 10.1 -> 14.4 | Improved |
| use PSPNet backbone or FastText embeddings instead of DeepLabV3+/word2vec (ablation) | uncertainty-aware ZSS · PC-30, PC-156, ADE-75 | unseen mIoU | Improved |
| exclude training images containing unseen classes (ablation) | baseline and uncertainty model · PC-30 vs PC-156, ADE-75 | unseen mIoU | Mixed |
Closest papers by meaning
- Zero-Shot Semantic Segmentation (NeurIPS 2019 · similarity 0.91)
- Decoupling Zero-Shot Semantic Segmentation (CVPR 2022 · similarity 0.90)
- Label-Efficient Few-Shot Semantic Segmentation with Unsupervised Meta-Training (AAAI 2024 · similarity 0.88)
- ValUES: A Framework for Systematic Validation of Uncertainty Estimation in Semantic Segmentation (ICLR 2024 · similarity 0.88)
- Generalized Zero-Shot Learning for Point Cloud Segmentation with Evidence-Based Dynamic Calibration (AAAI 2025 · similarity 0.88)
- Uncertainty-aware Fine-tuning of Segmentation Foundation Models (NeurIPS 2024 · 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.
