Research map / Image generation / Autoregressive and latent generation
Learning Multi-Instance Enriched Image Representations via Non-Greedy Ratio Maximization of the l1-Norm Distances
Kai Liu, Hua Wang, Feiping Nie, Hao Zhang
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 |
|---|---|---|---|
| Use the multi-instance enriched representation with SVM instead of the strongest baseline | Our method (SVM) · PASCAL VOC 2010 | Hamming loss: 0.173 ± 0.011 -> 0.155 ± 0.014 | Improved |
| Use the multi-instance enriched representation with SVM instead of the strongest baseline | Our method (SVM) · PASCAL VOC 2010 | One-error: 0.306 ± 0.018 -> 0.272 ± 0.011 | Improved |
| Use the multi-instance enriched representation with SVM instead of the strongest baseline | Our method (SVM) · PASCAL VOC 2010 | Average precision: 0.485 ± 0.022 -> 0.507 ± 0.015 | Improved |
| Use the multi-instance enriched representation with SVM instead of the strongest baseline | Our method (SVM) · Corel5K | Hamming loss: 0.238 ± 0.004 -> 0.204 ± 0.015 | Improved |
| Use the multi-instance enriched representation with SVM instead of the strongest baseline | Our method (SVM) · Corel5K | Average precision: 0.559 ± 0.018 -> 0.604 ± 0.010 | Improved |
| Use the multi-instance enriched representation with SVM instead of the strongest baseline | Our method (SVM) · Scene | Hamming loss: 0.215 ± 0.011 -> 0.175 ± 0.004 | Improved |
| Use the multi-instance enriched representation with SVM instead of the strongest baseline | Our method (SVM) · Scene | One-error: 0.370 ± 0.012 -> 0.355 ± 0.016 | Improved |
| Use the multi-instance enriched representation with SVM instead of the strongest baseline | Our method (SVM) · Scene | Average precision: 0.715 ± 0.033 -> 0.794 ± 0.011 | Improved |
Closest papers by meaning
- Learning Representations by Maximizing Mutual Information Across Views (NeurIPS 2019 · similarity 0.87)
- Large Scale Visual Recognition through Adaptation using Joint Representation and Multiple Instance Learning (JMLR 2016 · similarity 0.87)
- Beyond Supervised vs. Unsupervised: Representative Benchmarking and Analysis of Image Representation Learning (CVPR 2022 · similarity 0.86)
- Towards Efficient and Effective Self-Supervised Learning of Visual Representations (ECCV 2022 · similarity 0.86)
- Approximate Fisher Kernels of Non-iid Image Models for Image Categorization (TPAMI 2016 · similarity 0.85)
- Bag of Instances Aggregation Boosts Self-supervised Distillation (ICLR 2022 · 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.
