Research map / Vision-language and multimodal / Human and embodied modeling
MedKCO: Medical Vision-Language Pretraining via Knowledge-Driven Cognitive Orchestration
Chenran Zhang, Ruiqi Wu, Tao Zhou, Yi Zhou
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 MedKCO pretraining | CLIP · zero-shot avg (9 datasets) | accuracy/AUC: 0.616 -> 0.693 | Improved |
| add MedKCO pretraining | FILIP · zero-shot avg (9 datasets) | accuracy/AUC: 0.530 -> 0.640 | Improved |
| add MedKCO pretraining | CLIP · report generation avg | avg score: 0.188 -> 0.198 | Improved |
| add label-level curriculum (ablation) | CLIP · CFP ODIR200x3 | accuracy: 0.772 -> 0.847 | Improved |
| add description-level curriculum (ablation) | CLIP + label curriculum · CFP avg | avg: 0.820 -> 0.839 | Improved |
| add self-paced asymmetric loss (ablation) | CLIP + both curricula · CFP avg | avg: 0.839 -> 0.846 | Improved |
| add self-paced asymmetric loss (ablation) | CLIP + both curricula · CFP ODIR200x3 | accuracy: 0.890 -> 0.863 | Hurt |
| use global linear schedule instead of segmented (ablation) | MedKCO · CFP avg | avg: 0.805 -> 0.846 | Improved |
| divide stages by distance rather than sample count (ablation) | MedKCO · CFP avg | avg: 0.820 -> 0.846 | Improved |
| use 2 instead of 3 or 4 description-level stages (ablation) | MedKCO · CFP avg | avg: 0.820 -> 0.846 | Improved |
| use CL-log or CL-logit curriculum instead of random order | CLIP · zero-shot avg (9 datasets) | accuracy/AUC: 0.616 -> 0.600 | Hurt |
| add MedKCO pretraining | FILIP · ODIR200x3 | accuracy: 0.457 -> 0.833 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- FILIP — FILIP: Fine-grained Interactive Language-Image Pre-Training (ICLR 2022) · better on 5 of 5 shared results
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
- MedUnifier: Unifying Vision-and-Language Pre-training on Medical Data with Vision Generation Task using Discrete Visual Representations (CVPR 2025 · similarity 0.88)
- HealthGPT: A Medical Large Vision-Language Model for Unifying Comprehension and Generation via Heterogeneous Knowledge Adaptation (ICML 2025 · similarity 0.88)
- BiomedCoOp: Learning to Prompt for Biomedical Vision-Language Models (CVPR 2025 · similarity 0.88)
- VILA-M3: Enhancing Vision-Language Models with Medical Expert Knowledge (CVPR 2025 · similarity 0.88)
- MedSIGHT: Towards Grounded Visual Comprehension in Medical Large Vision-Language Models (ICML 2026 · similarity 0.87)
- MLIP: Enhancing Medical Visual Representation with Divergence Encoder and Knowledge-guided Contrastive Learning (CVPR 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.
