Research map / Detection and segmentation / Weakly supervised detection and segmentation
Variational Bayesian Multiple Instance Learning With Gaussian Processes
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 large-margin regularization (ablation) | VGPMIL · 20 Newsgroups | mAP: 0.65 -> 0.73 | Helped |
| Preprocess inputs with kernel PCA (ablation) | VGPMIL · 20 Newsgroups | mAP: 0.65 -> 0.72 | Helped |
| Add large-margin regularization (ablation) | VGPMIL · Barrett's cancer | Accuracy (in %): 75.1 -> 77.3 | Helped |
| Add large-margin regularization (ablation) | VGPMIL · PASCAL VOC 2007 | mAP: 46.1 -> 43.1 | Hurt |
| Add large-margin regularization (ablation) | VGPMIL · PASCAL VOC 2012 | mAP: 34.6 -> 37.8 | Helped |
| Use the multiclass output version instead of the binary output version (ablation) | VGPMIL object detection pipeline · PASCAL VOC 2007 | mAP | No clear effect |
| Combine weak bag labels with a small portion of strong instance labels | VGPMIL · PASCAL VOC 2007 | mAP | Helped |
| Use the VGPMIL pipeline's region proposals with Li et al.'s model | Li et al. model · PASCAL VOC 2007 test | mAP: 39.5 -> 31.9 | Hurt |
| Replace VGPMIL with an instance-prediction version of DMIL | VGPMIL object detection pipeline · PASCAL VOC 2007 test | mAP: 46.1 -> 36.7 | Hurt |
Closest papers by meaning
- Multi-Instance Causal Representation Learning for Instance Label Prediction and Out-of-Distribution Generalization (NeurIPS 2022 · similarity 0.86)
- Bag Graph: Multiple Instance Learning Using Bayesian Graph Neural Networks (AAAI 2022 · similarity 0.86)
- Not All Instances Should Contribute Equally: Sparse Support Grounding via Unbalanced Transport for Heterogeneous MIL (NeurIPS 2026 · similarity 0.86)
- Sm: enhanced localization in Multiple Instance Learning for medical imaging classification (NeurIPS 2024 · similarity 0.85)
- A Gaussian Process-Bayesian Bernoulli Mixture Model for Multi-Label Active Learning (NeurIPS 2021 · similarity 0.84)
- Bayesian Exploration of Pre-trained Models for Low-shot Image Classification (CVPR 2024 · similarity 0.83)
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.