Research map / Label-efficient and robust learning / Self-supervised and contrastive
When Does Self-supervision Improve Few-shot Learning?
Jong-Chyi Su, Subhransu Maji, Bharath Hariharan
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 jigsaw puzzle auxiliary loss (ablation) | ProtoNet · 7 few-shot datasets (5-way 5-shot) | accuracy: relative error reduced by 4.0%, 8.7%, 19.7%, 8.4%, 4.7%, 15.9%, 27.8% | Improved |
| add rotation prediction auxiliary loss (ablation) | ProtoNet · aircrafts and flowers (5-way 5-shot) | accuracy: 91.4 -> 91.4 (aircrafts); 89.2 -> 89.0 (flowers) | No clear effect |
| add jigsaw and rotation together (ablation) | ProtoNet · 7 few-shot datasets (5-way 5-shot) | accuracy: tiered-ImageNet 78.0 -> 77.2; Birds 89.8 -> 90.2 | Mixed |
| add jigsaw loss to other meta-learners (ablation) | Softmax, MAML, ProtoNet · 5 fine-grained datasets avg (5-way 5-shot) | accuracy: 85.5 -> 86.6; 82.6 -> 83.8; 88.5 -> 90.4 | Improved |
| add jigsaw loss on degraded images (Birds greyscale, Cars low-res) (ablation) | ProtoNet · degraded datasets (5-way 5-shot) | accuracy: 82.2 -> 85.4 (Birds greyscale); 84.8 -> 87.0 (Cars low-res) | Improved |
| add jigsaw loss with only 20% of base images (ablation) | ProtoNet · 20% Cars (5-way 5-shot) | accuracy: 75.8 -> 82.8; gain 0.7% -> 7.0% | Improved |
| add jigsaw loss with only 20% of base images (ablation) | ProtoNet · 20% Aircrafts (5-way 5-shot) | accuracy: 77.7 -> 78.4 | No clear effect |
| use self-supervision alone instead of supervised labels (ablation) | ResNet-18 · fine-grained avg (5-way 5-shot) | accuracy: 85.5 -> 32.9 (jigsaw); 85.5 -> 33.7 (rotation) | Hurt |
| initialize with SSL before meta-learning instead of random init (ablation) | ProtoNet · few-shot benchmarks | accuracy | No clear effect |
| replace fraction of SSL images with out-of-domain images (ablation) | ProtoNet + Jigsaw · 20% base set, 5 datasets | accuracy | Hurt |
| add more unlabeled in-domain images for SSL (20% to 100%) (ablation) | ProtoNet + Jigsaw · 20% base set | accuracy | Improved |
| add random pool images for SSL (ablation) | ProtoNet + Jigsaw · 20% Cars/Dogs/Flowers | accuracy: 82.1 -> 78.4 (Cars); 71.8 -> 68.5 (Dogs); 85.9 -> 83.5 (Flowers) | Hurt |
Closest papers by meaning
- A Closer Look at Benchmarking Self-supervised Pre-training with Image Classification (IJCV 2025 · similarity 0.92)
- Boosting Few-Shot Visual Learning With Self-Supervision (ICCV 2019 · similarity 0.90)
- Dynamic Data Selection for Efficient SSL via Coarse-to-Fine Refinement (ECCV 2024 · similarity 0.89)
- Few-Shot Learning With a Strong Teacher (TPAMI 2022 · similarity 0.89)
- Self-Supervision Can Be a Good Few-Shot Learner (ECCV 2022 · similarity 0.89)
- Views Can Be Deceiving: Improved SSL Through Feature Space Augmentation (ICLR 2024 · similarity 0.86)
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.
