# CAMANet: Class Activation Map Guided Attention Network for Radiology Report Generation

arXiv: https://arxiv.org/abs/2211.01412 · HTML: https://mlsanity.com/paper/2211.01412/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 57 references that are in the map.
- First posted on arXiv 2 Nov 2022.

## Builds on (most cited first, 30 of 39)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison](https://mlsanity.com/paper/1901.07031/) (2019)
- [Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering](https://mlsanity.com/paper/1707.07998/) (2017)
- [Self-critical Sequence Training for Image Captioning](https://mlsanity.com/paper/1612.00563/) (2016)
- [Generating Radiology Reports via Memory-driven Transformer](https://mlsanity.com/paper/2010.16056/) (2020)
- [Meshed-Memory Transformer for Image Captioning](https://mlsanity.com/paper/1912.08226/) (2019)
- [Making the Most of Text Semantics to Improve Biomedical Vision--Language Processing](https://mlsanity.com/paper/2204.09817/) (2022)
- [CheXbert: Combining Automatic Labelers and Expert Annotations for Accurate Radiology Report Labeling Using BERT](https://mlsanity.com/paper/2004.09167/) (2020)
- [An Empirical Study of Training End-to-End Vision-and-Language Transformers](https://mlsanity.com/paper/2111.02387/) (2021)
- [Knowing When to Look: Adaptive Attention via A Visual Sentinel for Image Captioning](https://mlsanity.com/paper/1612.01887/) (2016)
- [On the Automatic Generation of Medical Imaging Reports](https://mlsanity.com/paper/1711.08195/) (2017)
- [X-Linear Attention Networks for Image Captioning](https://mlsanity.com/paper/2003.14080/) (2020)
- [Cross-modal Memory Networks for Radiology Report Generation](https://mlsanity.com/paper/2204.13258/) (2022)
- [Exploring and Distilling Posterior and Prior Knowledge for Radiology Report Generation](https://mlsanity.com/paper/2106.06963/) (2021)
- [When Radiology Report Generation Meets Knowledge Graph](https://mlsanity.com/paper/2002.08277/) (2020)
- [Hybrid Retrieval-Generation Reinforced Agent for Medical Image Report Generation](https://mlsanity.com/paper/1805.08298/) (2018)
- [Clinically Accurate Chest X-Ray Report Generation](https://mlsanity.com/paper/1904.02633/) (2019)
- [Learning Affinity from Attention: End-to-End Weakly-Supervised Semantic Segmentation with Transformers](https://mlsanity.com/paper/2203.02664/) (2022)
- [Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone](https://mlsanity.com/paper/2206.07643/) (2022)
- [A Hierarchical Approach for Generating Descriptive Image Paragraphs](https://mlsanity.com/paper/1611.06607/) (2016)
- [Knowledge-driven Encode, Retrieve, Paraphrase for Medical Image Report Generation](https://mlsanity.com/paper/1903.10122/) (2019)
- [Multi-modal Understanding and Generation for Medical Images and Text via Vision-Language Pre-Training](https://mlsanity.com/paper/2105.11333/) (2021)
- [Competence-based Multimodal Curriculum Learning for Medical Report Generation](https://mlsanity.com/paper/2206.14579/) (2022)

## Built on by (most cited first, 22 of 22)

- [CXPMRG-Bench: Pre-training and Benchmarking for X-ray Medical Report Generation on CheXpert Plus Dataset](https://mlsanity.com/paper/2410.00379/) (2024)
- [Cross-Modal Causal Intervention for Medical Report Generation](https://mlsanity.com/paper/2303.09117/) (2023)
- [Guided Interpretable Facial Expression Recognition via Spatial Action Unit Cues](https://mlsanity.com/paper/2402.00281/) (2024)
- [Factual Serialization Enhancement: A Key Innovation for Chest X-ray Report Generation](https://mlsanity.com/paper/2405.09586/) (2024)
- [A Survey of Medical Vision-and-Language Applications and Their Techniques](https://mlsanity.com/paper/2411.12195/) (2024)
- [A Survey of Deep Learning-based Radiology Report Generation Using Multimodal Data](https://mlsanity.com/paper/2405.12833/) (2024)
- [A Disease-Aware Dual-Stage Framework for Chest X-ray Report Generation](https://mlsanity.com/paper/2511.12259/) (2025)
- [MvKeTR: Chest CT Report Generation with Multi-View Perception and Knowledge Enhancement](https://mlsanity.com/paper/2411.18309/) (2024)
- [EMRRG: Efficient Fine-Tuning Pre-trained X-ray Mamba Networks for Radiology Report Generation](https://mlsanity.com/paper/2510.16776/) (2025)
- [Anatomy-Guided Radiology Report Generation with Pathology-Aware Regional Prompts](https://mlsanity.com/paper/2411.10789/) (2024)
- [Scene Graph Aided Radiology Report Generation](https://mlsanity.com/paper/2403.05687/) (2024)
- [Cyclic Vision-Language Manipulator: Towards Reliable and Fine-Grained Image Interpretation for Automated Report Generation](https://mlsanity.com/paper/2411.05261/) (2024)
- [Improving Medical Visual Representation Learning with Pathological-level Cross-Modal Alignment and Correlation Exploration](https://mlsanity.com/paper/2506.10573/) (2025)
- [OraPO: Oracle-educated Reinforcement Learning for Data-efficient and Factual Radiology Report Generation](https://mlsanity.com/paper/2509.18600/) (2025)
- [RIHA: Report-Image Hierarchical Alignment for Radiology Report Generation](https://mlsanity.com/paper/2604.27559/) (2026)
- [Graph-Augmented Topological Internalization with Dual-Stream Classifiers for Medical Report Generation](https://mlsanity.com/paper/2605.02376/) (2026)
- [Seeing What Matters: Lesion-Aware High-Resolution Patch Discovery and Fusion for Chest X-ray Report Generation](https://mlsanity.com/paper/2607.06909/) (2026)
- [Semantically Informed Salient Regions Guided Radiology Report Generation](https://mlsanity.com/paper/2507.11015/) (2025)
- [Scaling Down to Scale Up: Towards Operationally-Efficient and Deployable Clinical Models via Cross-Modal Low-Rank Adaptation for Medical Vision-Language Models](https://mlsanity.com/paper/2512.00597/) (2025)
- [Rethinking the Efficiency and Effectiveness of Reinforcement Learning for Radiology Report Generation](https://mlsanity.com/paper/2603.04022/) (2026)
- [Seeing Through Multiple Views: Parameter-Efficient Fine-Tuning via Selective Neurons for Consistent Radiology Report Generation](https://mlsanity.com/paper/2606.31099/) (2026)
- [Pre-training, Reasoning, Benchmarking: X-ray Report Generation on CheXpert Plus Dataset](https://mlsanity.com/paper/2610.08813/) (2026)

## Abstract (arXiv)

Radiology report generation (RRG) has gained increasing research attention because of its huge potential to mitigate medical resource shortages and aid the process of disease decision making by radiologists. Recent advancements in RRG are largely driven by improving a model's capabilities in encoding single-modal feature representations, while few studies explicitly explore the cross-modal alignment between image regions and words. Radiologists typically focus first on abnormal image regions before composing the corresponding text descriptions, thus cross-modal alignment is of great importance to learn a RRG model which is aware of abnormalities in the image. Motivated by this, we propose a Class Activation Map guided Attention Network (CAMANet) which explicitly promotes crossmodal alignment by employing aggregated class activation maps to supervise cross-modal attention learning, and simultaneously enrich the discriminative information. CAMANet contains three complementary modules: a Visual Discriminative Map Generation module to generate the importance/contribution of each visual token; Visual Discriminative Map Assisted Encoder to learn the discriminative representation and enrich the discriminative information; and a Visual Textual Attention Consistency module to ensure the attention consistency between the visual and textual tokens, to achieve the cross-modal alignment. Experimental results demonstrate that CAMANet outperforms previous SOTA methods on two commonly used RRG benchmarks.