Research map / Label-efficient and robust learning / Recognition and long-tail
MetaSAug: Meta Semantic Augmentation for Long-Tailed Visual Recognition
Shuang Li, Kaixiong Gong, Chi Harold Liu, Yulin Wang, Feng Qiao, Xinjing Cheng
Check 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 re-weighting to MetaSAug (ablation) | MetaSAug with cross-entropy loss · CIFAR-LT-10, imbalance factors 100, 50, 20 | top-1 error (%): 25.96 -> 19.46; 20.63 -> 15.97; 15.15 -> 12.36 | Improved |
| Add meta-learning to learn class-wise covariance (ablation) | MetaSAug with cross-entropy loss · CIFAR-LT-10, imbalance factors 100, 50, 20 | top-1 error (%): 21.68 -> 19.46; 17.43 -> 15.97; 13.08 -> 12.36 | Improved |
| Learn covariance with MetaSAug rather than using fixed ISDA with L2RW (ablation) | CIFAR-LT-10 cross-entropy training · CIFAR-LT-10, imbalance factors 100, 50, 20 | top-1 error (%): 25.16 -> 19.46; 20.78 -> 15.97; 16.53 -> 12.36 | Improved |
| Learn covariance with MetaSAug rather than using fixed ISDA with Meta-weight-net (ablation) | CIFAR-LT-10 cross-entropy training · CIFAR-LT-10, imbalance factors 100, 50, 20 | top-1 error (%): 24.69 -> 19.46; 20.42 -> 15.97; 14.71 -> 12.36 | Improved |
| Learn covariance with MetaSAug rather than using fixed ISDA with meta-class-weight (ablation) | CIFAR-LT-10 cross-entropy training · CIFAR-LT-10, imbalance factors 100, 50, 20 | top-1 error (%): 20.78 -> 19.46; 17.12 -> 15.97; 12.93 -> 12.36 | Improved |
Later papers that compared with this method
2 later accepted papers report MetaSAug as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.
- Class and Attribute-Aware Logit Adjustment for Generalized Long-Tail Learning (AAAI 2025 · better on 1 of 1 shared result)
- Imagine by Reasoning: A Reasoning-Based Implicit Semantic Data Augmentation for Long-Tailed Classification (AAAI 2022 · 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
- Imagine by Reasoning: A Reasoning-Based Implicit Semantic Data Augmentation for Long-Tailed Classification (AAAI 2022 · similarity 0.89)
- Regularizing Deep Networks with Semantic Data Augmentation (TPAMI 2021 · similarity 0.89)
- Semantic-Guided Generative Image Augmentation Method with Diffusion Models for Image Classification (AAAI 2024 · similarity 0.86)
- Effective Data Augmentation With Diffusion Models (ICLR 2024 · similarity 0.86)
- Beyond Words: Augmenting Discriminative Richness via Diffusions in Unsupervised Prompt Learning (CVPR 2025 · similarity 0.86)
- Context-Aware Meta-Learning (ICLR 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.
