Research map / Label-efficient and robust learning / Recognition and long-tail
TieNet: Text-Image Embedding Network for Common Thorax Disease Classification and Reporting in Chest X-Rays
Read the paperCheck 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 |
|---|---|---|---|
| Use paired image and report inputs instead of reports alone | TieNet auto-annotation · ChestX-ray14 | AUC (#wAVG): .978 -> .992 | Helped |
| Use paired image and report inputs instead of reports alone | TieNet auto-annotation · Hand-labeled | AUC (#wAVG): .878 -> .900 | Helped |
| Use paired image and report inputs instead of reports alone | TieNet auto-annotation · OpenI | AUC (#wAVG): .957 -> .966 | Helped |
| Train with reports and generate reports from images at test time instead of using the image baseline | TieNet I+GR · ChestX-ray14 | AUC (#wAVG): .722 -> .748 | Helped |
| Train with reports and generate reports from images at test time instead of using the image baseline | TieNet I+GR · Hand-labeled | AUC (#wAVG): .687 -> .719 | Helped |
| Train with reports and generate reports from images at test time instead of using the image baseline | TieNet I+GR · OpenI | AUC (#wAVG): .741 -> .798 | Helped |
| Jointly train image classification and report generation | TieNet I+GR · ChestX-ray14 test | BLEU-1: 0.2391 -> 0.2860 | Helped |
| Jointly train image classification and report generation | TieNet I+GR · ChestX-ray14 test | BLEU-2: 0.1248 -> 0.1597 | Helped |
| Jointly train image classification and report generation | TieNet I+GR · ChestX-ray14 test | BLEU-3: 0.0861 -> 0.1038 | Helped |
| Jointly train image classification and report generation | TieNet I+GR · ChestX-ray14 test | BLEU-4: 0.0658 -> 0.0736 | Helped |
| Jointly train image classification and report generation | TieNet I+GR · ChestX-ray14 test | METEOR: 0.1024 -> 0.1076 | Helped |
| Jointly train image classification and report generation | TieNet I+GR · ChestX-ray14 test | ROUGE-L: 0.1988 -> 0.2263 | Helped |
Closest papers by meaning
- Bootstrapping Chest CT Image Understanding by Distilling Knowledge from X-ray Expert Models (CVPR 2024 · similarity 0.89)
- Novel Class Discovery in Chest X-rays via Paired Images and Text (AAAI 2024 · similarity 0.88)
- Learning Low-Rank Feature for Thorax Disease Classification (NeurIPS 2024 · similarity 0.87)
- Large-scale and Fine-grained Vision-language Pre-training for Enhanced CT Image Understanding (ICLR 2025 · similarity 0.87)
- From Complexity to Clarity: Transforming Chest X-ray Reports with Chained Prompting (Student Abstract) (AAAI 2025 · similarity 0.86)
- BenchX: A Unified Benchmark Framework for Medical Vision-Language Pretraining on Chest X-Rays (NeurIPS 2024 · similarity 0.86)
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.