# YONA: You Only Need One Adjacent Reference-frame for Accurate and Fast Video Polyp Detection

arXiv: https://arxiv.org/abs/2306.03686 · HTML: https://mlsanity.com/paper/2306.03686/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 29 references that are in the map.
- First posted on arXiv 6 Jun 2023.

## Builds on (most cited first, 16 of 16)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [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)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [Deformable Convolutional Networks](https://mlsanity.com/paper/1703.06211/) (2017)
- [DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection](https://mlsanity.com/paper/2203.03605/) (2022)
- [Objects as Points](https://mlsanity.com/paper/1904.07850/) (2019)
- [Dual Attention Network for Scene Segmentation](https://mlsanity.com/paper/1809.02983/) (2018)
- [Sparse R-CNN: End-to-End Object Detection with Learnable Proposals](https://mlsanity.com/paper/2011.12450/) (2020)
- [Exploring Cross-Image Pixel Contrast for Semantic Segmentation](https://mlsanity.com/paper/2101.11939/) (2021)
- [Flow-Guided Feature Aggregation for Video Object Detection](https://mlsanity.com/paper/1703.10025/) (2017)
- [Memory Enhanced Global-Local Aggregation for Video Object Detection](https://mlsanity.com/paper/2003.12063/) (2020)
- [TransVOD: End-to-End Video Object Detection with Spatial-Temporal Transformers](https://mlsanity.com/paper/2201.05047/) (2022)
- [Cosine Normalization: Using Cosine Similarity Instead of Dot Product in Neural Networks](https://mlsanity.com/paper/1702.05870/) (2017)
- [Multi-frame Collaboration for Effective Endoscopic Video Polyp Detection via Spatial-Temporal Feature Transformation](https://mlsanity.com/paper/2107.03609/) (2021)

## Built on by (most cited first, 7 of 7)

- [Frontiers in Intelligent Colonoscopy](https://mlsanity.com/paper/2410.17241/) (2024)
- [Segment Anything Model-guided Collaborative Learning Network for Scribble-supervised Polyp Segmentation](https://mlsanity.com/paper/2312.00312/) (2023)
- [Let Video Teaches You More: Video-to-Image Knowledge Distillation using DEtection TRansformer for Medical Video Lesion Detection](https://mlsanity.com/paper/2408.14051/) (2024)
- [Consisaug: A Consistency-based Augmentation for Polyp Detection in Endoscopy Image Analysis](https://mlsanity.com/paper/2404.11355/) (2024)
- [TSdetector: Temporal-Spatial Self-correction Collaborative Learning for Colonoscopy Video Detection](https://mlsanity.com/paper/2409.19983/) (2024)
- [AVPDN: Learning Motion-Robust and Scale-Adaptive Representations for Video-Based Polyp Detection](https://mlsanity.com/paper/2508.03458/) (2025)
- [A multi-center analysis of deep learning methods for video polyp detection and segmentation](https://mlsanity.com/paper/2603.04288/) (2026)

## Abstract (arXiv)

Accurate polyp detection is essential for assisting clinical rectal cancer diagnoses. Colonoscopy videos contain richer information than still images, making them a valuable resource for deep learning methods. Great efforts have been made to conduct video polyp detection through multi-frame temporal/spatial aggregation. However, unlike common fixed-camera video, the camera-moving scene in colonoscopy videos can cause rapid video jitters, leading to unstable training for existing video detection models. Additionally, the concealed nature of some polyps and the complex background environment further hinder the performance of existing video detectors. In this paper, we propose the YONA (You Only Need one Adjacent Reference-frame) method, an efficient end-to-end training framework for video polyp detection. YONA fully exploits the information of one previous adjacent frame and conducts polyp detection on the current frame without multi-frame collaborations. Specifically, for the foreground, YONA adaptively aligns the current frame's channel activation patterns with its adjacent reference frames according to their foreground similarity. For the background, YONA conducts background dynamic alignment guided by inter-frame difference to eliminate the invalid features produced by drastic spatial jitters. Moreover, YONA applies cross-frame contrastive learning during training, leveraging the ground truth bounding box to improve the model's perception of polyp and background. Quantitative and qualitative experiments on three public challenging benchmarks demonstrate that our proposed YONA outperforms previous state-of-the-art competitors by a large margin in both accuracy and speed.