# CPR: Chained Perceptual Refinement for Coarse-to-Fine Medical Image Classification

arXiv: https://arxiv.org/abs/2607.02591 · HTML: https://mlsanity.com/paper/2607.02591/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 29 references that are in the map.
- First posted on arXiv 1 Jul 2026.

## Builds on (most cited first, 15 of 15)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles](https://mlsanity.com/paper/2306.00989/) (2023)
- [Can AI help in screening Viral and COVID-19 pneumonia?](https://mlsanity.com/paper/2003.13145/) (2020)
- [ZoomNeXt: A Unified Collaborative Pyramid Network for Camouflaged Object Detection](https://mlsanity.com/paper/2310.20208/) (2023)
- [Mammo-CLIP: A Vision Language Foundation Model to Enhance Data Efficiency and Robustness in Mammography](https://mlsanity.com/paper/2405.12255/) (2024)
- [OverLoCK: An Overview-first-Look-Closely-next ConvNet with Context-Mixing Dynamic Kernels](https://mlsanity.com/paper/2502.20087/) (2025)
- [Hard-Attention for Scalable Image Classification](https://mlsanity.com/paper/2102.10212/) (2021)
- [Emulating Human-like Adaptive Vision for Efficient and Flexible Machine Visual Perception](https://mlsanity.com/paper/2509.15333/) (2025)
- [Dynamic Policy-Driven Adaptive Multi-Instance Learning for Whole Slide Image Classification](https://mlsanity.com/paper/2403.07939/) (2024)
- [Focus Longer to See Better:Recursively Refined Attention for Fine-Grained Image Classification](https://mlsanity.com/paper/2005.10979/) (2020)
- [M2Former: Multi-Scale Patch Selection for Fine-Grained Visual Recognition](https://mlsanity.com/paper/2308.02161/) (2023)
- [Revisiting the Integration of Convolution and Attention for Vision Backbone](https://mlsanity.com/paper/2411.14429/) (2024)
- [A Spatially-Aware Multiple Instance Learning Framework for Digital Pathology](https://mlsanity.com/paper/2504.17379/) (2025)

## Abstract (arXiv)

High resolution medical images contain fine grained, spatially sparse cues that are critical for diagnosis, yet preserving full resolution incurs substantial computational and memory costs. Most deep models process images uniformly, leading to redundant computation or loss of diagnostic detail under downsampling. We propose Chained Perceptual Refinement, CPR, a coarse to fine framework that formulates medical image analysis as a sequential global to local decision process. Starting from a low resolution global view, CPR dynamically predicts the location and spatial extent of refinement regions, extracts high resolution evidence from the original image, and incrementally integrates it with global context. By keeping the backbone input size fixed while contracting the perceptual field, CPR preserves diagnostic fidelity with constant peak GPU memory. Extensive experiments on five medical imaging datasets and multiple backbone architectures demonstrate that CPR consistently outperforms both fixed resolution and multi scale state of the art baselines, achieving improvements of up to 2.27 percentage points over the second best method. It also achieves up to a 19.6 fold reduction in GFLOPs at matched accuracy, establishing a superior accuracy and efficiency trade off for high resolution medical image analysis. The code is available on GitHub.