Research map / Continual learning / Class-incremental
Fairness Continual Learning Approach to Semantic Scene Understanding in Open-World Environments
Thanh-Dat Truong, Hoang-Quan Nguyen, Bhiksha Raj, Khoa Luu
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 prototypical contrastive clustering loss L_cluster (ablation) | FairCL DeepLab-V3 · ADE20K 100-50 | mIoU all: 6.52 -> 32.97 | Improved |
| add prototypical contrastive clustering loss L_cluster (ablation) | FairCL SegFormer · ADE20K 100-50 | mIoU all: 7.74 -> 36.18 | Improved |
| add fairness loss L_class (ablation) | FairCL DeepLab-V3 · ADE20K 100-50 | mIoU all: 32.97 -> 34.40 | Improved |
| add fairness loss L_class (ablation) | FairCL SegFormer · ADE20K 100-50 | mIoU all: 36.18 -> 36.78 | Improved |
| add fairness loss L_class (ablation) | FairCL · ADE20K 100-50 | STD of IoU: reduced by 0.96% and 0.46% | Improved |
| add conditional structural consistency loss L_cons (ablation) | FairCL DeepLab-V3 · ADE20K 100-50 | mIoU all: 34.40 -> 36.99 | Improved |
| add conditional structural consistency loss L_cons (ablation) | FairCL SegFormer · ADE20K 100-50 classes 101-150 | mIoU: 23.50 -> 25.46 | Improved |
| add L_cons (ablation) | FairCL SegFormer · ADE20K 100-50 classes 0-100 | mIoU: 43.35 -> 43.56 | Improved |
| add L_cluster (ablation) | FairCL · ADE20K 100-50 STD | STD of IoU: 19.90 -> 23.03 | Hurt |
| replace DeepLab-V3 ResNet101 with SegFormer MiT-B3 | FairCL · ADE20K 100-50 | mIoU classes 101-150: 19.86% to 25.46% | Improved |
| vary margin Delta from 10 to 5 or 15 (ablation) | FairCL · ADE20K 100-50 | mIoU all: 36.99 -> 36.68 | No clear effect |
| add L_class and L_cons to L_cluster (ablation) | FairCL DeepLab-V3 · ADE20K minor group | mIoU: 25.13 -> 30.52 | Improved |
Closest papers by meaning
- FALCON: Fairness Learning via Contrastive Attention Approach to Continual Semantic Scene Understanding (CVPR 2025 · similarity 0.93)
- Class Similarity Weighted Knowledge Distillation for Continual Semantic Segmentation (CVPR 2022 · similarity 0.89)
- Preparing the Future for Continual Semantic Segmentation (ICCV 2023 · similarity 0.88)
- Towards Continual Universal Segmentation (CVPR 2025 · similarity 0.87)
- Beyond Background Shift: Rethinking Instance Replay in Continual Semantic Segmentation (CVPR 2025 · similarity 0.87)
- Continual Segmentation with Disentangled Objectness Learning and Class Recognition (CVPR 2024 · similarity 0.85)
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.
