Research map / Vision-language and multimodal / Human and embodied modeling
OLIVES Dataset: Ophthalmic Labels for Investigating Visual Eye Semantics
Mohit Prabhushankar, Kiran Premdat Kokilepersaud, Yash-yee Logan, Stephanie Trejo Corona, Ghassan AlRegib, Charles Wykoff
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 biomarker modality via joint training to OCT model | ResNet-18 OCT · DR/DME detection | balanced accuracy: 70.15% -> 82.33% | Improved |
| add clinical labels via joint training to OCT model | ResNet-18 OCT · DR/DME detection | balanced accuracy: 70.15% -> 75.92% | Improved |
| use biomarker features alone instead of OCT | MLP · DR/DME detection | balanced accuracy: 70.15% -> 79.87% | Improved |
| choose contrastive positives by clinical label (CST) instead of augmentations (SimCLR/MoCo/PCL) | supervised contrastive ResNet-18 · biomarker multi-label | AUROC: 0.770 -> 0.790 | Improved |
| choose contrastive positives by Eye ID instead of PCL | supervised contrastive ResNet-18 · PAVF biomarker | accuracy: 52.69% -> 65.56% | Improved |
| clinically chosen positives on IRF biomarker accuracy | supervised contrastive ResNet-18 · IRF biomarker | accuracy: 76.50% -> 75.53% | No clear effect |
| use OCT volume instead of fundus for treatment effect prediction | EfficientNet · treatment effect prediction | accuracy: 56.06% -> 60.65% | Improved |
Closest papers by meaning
- FOCUS: Benchmarking Retinal Model Generalization from Foundation Vision Encoders to Multimodal LLMs (NeurIPS 2026 · similarity 0.87)
- BIOMEDICA: An Open Biomedical Image-Caption Archive, Dataset, and Vision-Language Models Derived from Scientific Literature (CVPR 2025 · similarity 0.86)
- Like an Ophthalmologist: Dynamic Selection Driven Multi-View Learning for Diabetic Retinopathy Grading (AAAI 2025 · similarity 0.85)
- RVD: A Handheld Device-Based Fundus Video Dataset for Retinal Vessel Segmentation (NeurIPS 2023 · similarity 0.84)
- Deep Hierarchies and Invariant Disease-Indicative Feature Learning for Computer Aided Diagnosis of Multiple Fundus Diseases (AAAI 2025 · similarity 0.83)
- SIGraph: Saliency Image-Graph Network for Retinal Disease Classification in Fundus Image (AAAI 2025 · similarity 0.82)
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.
