polyp-regime-bench-models

Model Card

Does the "best" polyp detector stay the best if you train it differently? This repository releases every model from a controlled benchmark that answers that question: 12 detectors × 3 white-light colonoscopy datasets × 6 training regimes × 3 seeds = 648 best.pt checkpoints, together with cached per-image predictions and ensemble outputs. RT-DETR-X (seed 88) on two Kvasir-SEG test frames under the Scratch, Pretrained and Aug-10× regimes. Green = reference box, cyan = matched detection, pink = unmatched detection (score > 0.20, IoU ≥ 0.50). These examples are illustrative, not typical accuracy. Only the 648 completed canonical runs are included. Interrupted runs, last.pt files, worker logs…

Excerpt from the card by AI-for-Medicine-and-Health.

Identity and Version

Repository

AI-for-Medicine-and-Health/polyp-regime-bench-models

Publisher

AI-for-Medicine-and-Health

Task

Object detection

Modality

Image

Library

Not stated by the source

Parameters

Not stated by the source

Languages

rt-detr

Revision

b981fe616121096afa1d8160b0091ebd335b5dfe

First published

2026-10-01

Last updated

2026-10-02

Files and Weights

2,001 files, 44.9 GB in total. The weights are 648 files totalling 39.6 GB in pt.