Research map / Label-efficient and robust learning / Self-supervised and contrastive
Exploring Transferability of Self-Supervised Learning by Task Conflict Calibration
Huijie Guo, Jingyao Wang, Peizheng Guo, Xingchen Shen, Changwen Zheng, Wenwen Qiang
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 TC2 task conflict calibration | SimCLR · PACS average | accuracy: 83.3 -> 86.2 | Improved |
| add TC2 task conflict calibration | VICRegL · PACS average | accuracy: 84.3 -> 87.7 | Improved |
| add TC2 task conflict calibration | MAE · ColoredMNIST worst-group | accuracy: 84.0 -> 88.3 | Improved |
| add TC2 task conflict calibration | BYOL · VOC 07 detection | AP: 47.0 -> 50.7 | Improved |
| split each batch into two SSL tasks without conflict calibration | SimCLR trained on ImageNet-100 · CIFAR-100 transfer | Top-1 accuracy | Mixed |
| use 4 tasks per batch instead of 2, 8, 16 or 32 (ablation) | TC2 · CIFAR10 | accuracy | Improved |
| add bi-level optimization mechanism (ablation) | TC2 · ablation (Table 12) | accuracy | Improved |
| add both Lv and Lw losses (ablation) | TC2 · ablation (Table 12) | accuracy | 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.
- Barlow Twins — Barlow Twins: Self-Supervised Learning via Redundancy Reduction (ICML 2021) · better on 1 of 1 shared result
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
- Understanding the Transferability of Representations via Task-Relatedness (NeurIPS 2024 · similarity 0.88)
- Understanding the Learning Phases in Self-Supervised Learning via Critical Periods (ICLR 2026 · similarity 0.88)
- The SSL Interplay: Augmentations, Inductive Bias, and Generalization (ICML 2023 · similarity 0.87)
- Towards Consistent Multi-Task Learning: Unlocking the Potential of Task-Specific Parameters (CVPR 2025 · similarity 0.85)
- Provable Sample-Efficient Transfer Learning Conditional Diffusion Models via Representation Learning (NeurIPS 2025 · similarity 0.85)
- Exploiting Task Relationships in Continual Learning via Transferability-Aware Task Embeddings (NeurIPS 2025 · similarity 0.84)
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.
