# Adaptive Detector-Verifier Framework for Zero-Shot Polyp Detection in Open-World Settings

arXiv: https://arxiv.org/abs/2512.12492 · HTML: https://mlsanity.com/paper/2512.12492/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 46 references that are in the map.
- First posted on arXiv 13 Dec 2025.

## Builds on (most cited first, 20 of 20)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [Qwen-Image Technical Report](https://mlsanity.com/paper/2508.02324/) (2025)
- [Kvasir-SEG: A Segmented Polyp Dataset](https://mlsanity.com/paper/1911.07069/) (2019)
- [Domain Adaptation for Medical Image Analysis: A Survey](https://mlsanity.com/paper/2102.09508/) (2021)
- [Lumina-DiMOO: An Omni Diffusion Large Language Model for Multi-Modal Generation and Understanding](https://mlsanity.com/paper/2510.06308/) (2025)
- [VMT-Adapter: Parameter-Efficient Transfer Learning for Multi-Task Dense Scene Understanding](https://mlsanity.com/paper/2312.08733/) (2023)
- [ReAgent-V: A Reward-Driven Multi-Agent Framework for Video Understanding](https://mlsanity.com/paper/2506.01300/) (2025)
- [Lumina-mGPT 2.0: Stand-Alone AutoRegressive Image Modeling](https://mlsanity.com/paper/2507.17801/) (2025)
- [WcDT: World-centric Diffusion Transformer for Traffic Scene Generation](https://mlsanity.com/paper/2404.02082/) (2024)
- [Reasoning in Computer Vision: Taxonomy, Models, Tasks, and Methodologies](https://mlsanity.com/paper/2508.10523/) (2025)
- [Twin Co-Adaptive Dialogue for Progressive Image Generation](https://mlsanity.com/paper/2504.14868/) (2025)
- [TSCnet: A Text-driven Semantic-level Controllable Framework for Customized Low-Light Image Enhancement](https://mlsanity.com/paper/2503.08168/) (2025)
- [Abductive Inference in Retrieval-Augmented Language Models: Generating and Validating Missing Premises](https://mlsanity.com/paper/2511.04020/) (2025)
- [CenterMamba-SAM: Center-Prioritized Scanning and Temporal Prototypes for Brain Lesion Segmentation](https://mlsanity.com/paper/2511.01243/) (2025)
- [LLM-Driven Adaptive Source-Sink Identification and False Positive Mitigation for Static Analysis](https://mlsanity.com/paper/2511.04023/) (2025)
- [Hybrid Fuzzing with LLM-Guided Input Mutation and Semantic Feedback](https://mlsanity.com/paper/2511.03995/) (2025)
- [Free-Mask: A Novel Paradigm of Integration Between the Segmentation Diffusion Model and Image Editing](https://mlsanity.com/paper/2411.01819/) (2024)
- [StreetMath: Study of LLMs' Approximation Behaviors](https://mlsanity.com/paper/2510.25776/) (2025)

## Built on by (most cited first, 4 of 4)

- [EVLA: An Electro-Aware Multimodal Assistant for Physically-Grounded Driving Reasoning and Control](https://mlsanity.com/paper/2606.28938/) (2026)
- [A3M: Adaptive, Adversarial and Multi-Objective Learning for Strategic Bidding in Repeated Auctions](https://mlsanity.com/paper/2606.28943/) (2026)
- [Beyond Skepticism: Evaluating LLMs Pedagogical Intent Reasoning with the Adaptive Pedagogical Vigilance Framework](https://mlsanity.com/paper/2607.01581/) (2026)
- [FedCausal-Dyn: A Causal-Dynamic Paradigm for Federated Learning under Dynamic Feature Drift](https://mlsanity.com/paper/2607.09695/) (2026)

## Abstract (arXiv)

Polyp detectors trained on clean datasets often underperform in real-world endoscopy, where illumination changes, motion blur, and occlusions degrade image quality. Existing approaches struggle with the domain gap between controlled laboratory conditions and clinical practice, where adverse imaging conditions are prevalent. In this work, we propose AdaptiveDetector, a novel two-stage detector-verifier framework comprising a YOLOv11 detector with a vision-language model (VLM) verifier. The detector adaptively adjusts per-frame confidence thresholds under VLM guidance, while the verifier is fine-tuned with Group Relative Policy Optimization (GRPO) using an asymmetric, cost-sensitive reward function specifically designed to discourage missed detections -- a critical clinical requirement. To enable realistic assessment under challenging conditions, we construct a comprehensive synthetic testbed by systematically degrading clean datasets with adverse conditions commonly encountered in clinical practice, providing a rigorous benchmark for zero-shot evaluation. Extensive zero-shot evaluation on synthetically degraded CVC-ClinicDB and Kvasir-SEG images demonstrates that our approach improves recall by 14 to 22 percentage points over YOLO alone, while precision remains within 0.7 points below to 1.7 points above the baseline. This combination of adaptive thresholding and cost-sensitive reinforcement learning achieves clinically aligned, open-world polyp detection with substantially fewer false negatives, thereby reducing the risk of missed precancerous polyps and improving patient outcomes.