Research map / Label-efficient and robust learning / Semi-supervised learning
Semi-Supervised Semantic Segmentation With High- and Low-Level Consistency
Sudhanshu Mittal, Maxim Tatarchenko, Thomas Brox
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 s4GAN branch with unlabeled images (ablation) | DeepLabv2 · PASCAL VOC 5% labeled | mIoU: 56.8 -> 60.9 | Improved |
| add MLMT multi-label classification branch to s4GAN (ablation) | s4GAN · PASCAL VOC 5% labeled | mIoU: 60.9 -> 62.9 | Improved |
| add MLMT branch only without s4GAN (ablation) | DeepLabv2 · PASCAL VOC 5% labeled | mIoU: 56.8 -> 59.0 | Improved |
| use mean-teacher semi-supervised classifier instead of supervised CNN classifier (ablation) | s4GAN + classifier · PASCAL VOC 5% labeled | mIoU: 62.2 -> 62.9 | Improved |
| use learned classifier instead of pixel-count threshold heuristic (ablation) | s4GAN · PASCAL VOC 5% labeled | mIoU: 61.5 -> 62.9 | Improved |
| use feature matching loss instead of standard GAN loss (ablation) | CE generator loss · PASCAL VOC 1/50 | mIoU: 54.0 -> 55.4 | Improved |
| add self-training loss (ablation) | CE + FM · PASCAL VOC 1/50 | mIoU: 55.4 -> 58.1 | Improved |
| use single-stage joint GAN training instead of Hung et al. two-stage | s4GAN · PASCAL VOC 1/50 (COCO pre-trained) | mIoU: 57.2 -> 63.3 | Improved |
| add MLMT branch | s4GAN · Cityscapes | mIoU | No clear effect |
| add s4GAN branch | DeepLabv2 · Cityscapes 1/8 labeled | mIoU: 56.2 -> 59.3 | Improved |
| use all labeled data with s4GAN only | s4GAN · PASCAL VOC full labels | mIoU: 70.7 -> 71.2 | No clear effect |
| swap backbone to DeepLabv3+ | s4GAN + MLMT · PASCAL VOC 1/8 | mIoU: 67.3 -> 70.4 | Improved |
Closest papers by meaning
- Semi-supervised Semantic Segmentation via Strong-weak Dual-branch Network (ECCV 2020 · similarity 0.93)
- Semi-Supervised Semantic Segmentation under Label Noise via Diverse Learning Groups (ICCV 2023 · similarity 0.93)
- A Simple Baseline for Semi-Supervised Semantic Segmentation With Strong Data Augmentation (ICCV 2021 · similarity 0.92)
- Semi-Supervised Semantic Segmentation With Directional Context-Aware Consistency (CVPR 2021 · similarity 0.92)
- Semi-supervised Semantic Segmentation with Prototype-based Consistency Regularization (NeurIPS 2022 · similarity 0.92)
- Semi-Supervised Semantic Segmentation With Pixel-Level Contrastive Learning From a Class-Wise Memory Bank (ICCV 2021 · similarity 0.92)
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.
