Research map / Label-efficient and robust learning / Self-supervised and contrastive
On Learning Discriminative Features from Synthesized Data for Self-Supervised Fine-Grained Visual Recognition
Zihu Wang, Lingqiao Liu, Scott Ricardo Figueroa Weston, Samuel Tian, Peng Li
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 generated perturbed-pair contrastive loss on top of MoCo v2 | MoCo v2 · CUB-200 linear evaluation | top-1 accuracy: 63.98 -> 66.17 | Improved |
| add generated perturbed-pair contrastive loss on top of MoCo v2 | MoCo v2 · Stanford Cars linear evaluation | top-1 accuracy: 62.02 -> 65.60 | Improved |
| add generated perturbed-pair contrastive loss on top of SimSiam | SimSiam · CUB-200 linear evaluation | top-1 accuracy: 46.75 -> 57.80 | Improved |
| add method on label-scarce linear evaluation | MoCo v2 · average of three FGVR datasets | top-1 accuracy gain over MoCo v2: +3.31%, +4.27%, +5.51% with 100%, 50%, 20% labels | Improved |
| add method on non-fine-grained data | MoCo v2 · CIFAR-100 | top-1 accuracy: 61.79 -> 63.26 | Improved |
| add method on non-fine-grained data | MoCo v2 · ImageNet-100 | top-1 accuracy: 62.45 -> 64.02 | Improved |
| add low-variance dimension noise to Grad-CAM-guided noise (ablation) | Ours · Stanford Cars linear evaluation | top-1 accuracy: 64.18 -> 65.60 | Improved |
| add Grad-CAM-guided noise to low-variance noise (ablation) | Ours · FGVC-Aircraft linear evaluation | top-1 accuracy: 53.11 -> 55.28 | Improved |
| add reconstruction loss to MoCo v2 (ablation) | MoCo v2 · Stanford Cars linear evaluation | top-1 accuracy: less than 1% | Improved |
Closest papers by meaning
- Learning Separable Fine-Grained Representation via Dendrogram Construction from Coarse Labels for Fine-grained Visual Recognition (ICCV 2025 · similarity 0.89)
- Improving Fine-Grained Visual Recognition in Low Data Regimes via Self-Boosting Attention Mechanism (ECCV 2022 · similarity 0.88)
- An Erudite Fine-Grained Visual Classification Model (CVPR 2023 · similarity 0.88)
- Views Can Be Deceiving: Improved SSL Through Feature Space Augmentation (ICLR 2024 · similarity 0.86)
- Measuring Self-Supervised Representation Quality for Downstream Classification Using Discriminative Features (AAAI 2024 · similarity 0.86)
- A Theoretical Analysis of Self-Supervised Learning for Vision Transformers (ICLR 2025 · 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.
