Research map / Label-efficient and robust learning / Semi-supervised learning
Two Losses, One Goal: Balancing Conflict Gradients for Semi-supervised Semantic Segmentation
Rui Sun, Huayu Mai, Wangkai Li, Yujia Chen, Yuan Wang
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 POS (Pareto weighting) without MEO (ablation) | UniMatch V1 · Pascal 1/16 (92) | mIoU: 75.2 -> 77.0 | Improved |
| add POS without MEO (ablation) | UniMatch V1 · Pascal 1/8 (183) | mIoU: 77.2 -> 78.1 | Improved |
| add POS without MEO (ablation) | UniMatch V1 · COCO 1/512 | mIoU: 31.9 -> 33.4 | Improved |
| add POS without MEO (ablation) | UniMatch V1 · COCO 1/256 | mIoU: 38.9 -> 39.8 | Improved |
| add MEO on top of POS (ablation) | UniMatch V1 · Pascal 1/16 (92) | mIoU: 77.0 -> 77.6 | Improved |
| add MEO on top of POS (ablation) | UniMatch V1 · COCO 1/512 | mIoU: 33.4 -> 34.0 | Improved |
| add MEO on top of POS (ablation) | UniMatch V1 · Pascal 1/8 (183) | mIoU: 78.1 -> 78.7 | Improved |
| add MEO on top of POS (ablation) | UniMatch V1 · COCO 1/256 | mIoU: 39.8 -> 40.3 | Improved |
| replace fixed weights (2:1) with dynamic POS weights (ablation) | UniMatch V1 · Pascal 1/16 (92) | mIoU: 74.9 -> 77.6 | Improved |
| replace fixed weights (1:2) with dynamic POS weights (ablation) | UniMatch V1 · Pascal 1/16 (92) | mIoU: 74.1 -> 77.6 | Improved |
| replace equal fixed weights with dynamic POS weights (ablation) | UniMatch V1 · Pascal 1/16 (92) | mIoU: 75.2 -> 77.6 | Improved |
| add POS+MEO to UniMatch V2 (DINOv2-S) | UniMatch V2 · Pascal 1/16 (92) | mIoU: 79.0 -> 80.7 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- UniMatch V1 — UniMatch: Universal Matching from Atom to Task for Few-Shot Drug Discovery (ICLR 2025) · better on 10 of 10 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Semi-Supervised Semantic Segmentation With High- and Low-Level Consistency (TPAMI 2019 · similarity 0.90)
- DAW: Exploring the Better Weighting Function for Semi-supervised Semantic Segmentation (NeurIPS 2023 · similarity 0.89)
- Universal Semi-Supervised Semantic Segmentation (ICCV 2019 · similarity 0.89)
- A Simple Baseline for Semi-Supervised Semantic Segmentation With Strong Data Augmentation (ICCV 2021 · similarity 0.89)
- Improving Semi-Supervised Semantic Segmentation with Sliced-Wasserstein Feature Alignment and Uniformity (CVPR 2025 · similarity 0.89)
- Diffusion-Driven Two-Stage Active Learning for Low-Budget Semantic Segmentation (NeurIPS 2025 · similarity 0.88)
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.
