Research map / Label-efficient and robust learning / Recognition and long-tail
Inflated Episodic Memory With Region Self-Attention for Long-Tailed Visual Recognition
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 IEM with region self-attention | long-tailed image classification models · ImageNet-LT closed-set | accuracy: 35.6 -> 43.2 | Helped |
| add IEM with region self-attention | long-tailed image classification models · ImageNet-LT open-set | F-measure: 0.474 -> 0.525 | Helped |
| add IEM with region self-attention | long-tailed image classification models · Places-LT closed-set | accuracy: 35.9 -> 39.7 | Helped |
| add IEM with region self-attention | long-tailed image classification models · Places-LT open-set | F-measure: 0.464 -> 0.486 | Helped |
| add IEM with region self-attention | long-tailed image classification models · SUN-LT | accuracy: 58.7 -> 60.2 | Helped |
| add IEM with region self-attention | ResNet-50 · iNaturalist | accuracy: 68.0 -> 70.2 | Helped |
| add IEM to NetVLAD | NetVLAD · YouTube-8M | GAP: 86.1 -> 87.7 | Helped |
| add IEM to NetVLAD | NetVLAD · YouTube-8M | mAP: 52.7 -> 56.5 | Helped |
| add region self-attention instead of average pooling (ablation) | IEM image classifiers · ImageNet-LT | accuracy: 41.7 -> 43.2 | Helped |
| add region self-attention instead of average pooling (ablation) | IEM image classifiers · Places-LT | accuracy: 31.1 -> 39.7 | Helped |
| add region self-attention instead of average pooling (ablation) | IEM image classifiers · SUN-LT | accuracy: 59.3 -> 60.2 | Helped |
| add region self-attention instead of average pooling (ablation) | IEM image classifiers · iNaturalist | accuracy: 69.5 -> 70.2 | Helped |
Closest papers by meaning
- Bag of Tricks for Long-Tailed Visual Recognition with Deep Convolutional Neural Networks (AAAI 2021 · similarity 0.91)
- Large-Scale Long-Tailed Recognition in an Open World (CVPR 2019 · similarity 0.89)
- Global and Local Mixture Consistency Cumulative Learning for Long-Tailed Visual Recognitions (CVPR 2023 · similarity 0.88)
- Feature Fusion from Head to Tail for Long-Tailed Visual Recognition (AAAI 2024 · similarity 0.88)
- Improving Visual Prompt Tuning by Gaussian Neighborhood Minimization for Long-Tailed Visual Recognition (NeurIPS 2024 · similarity 0.88)
- DiffuLT: Diffusion for Long-tail Recognition Without External Knowledge (NeurIPS 2024 · similarity 0.87)
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.