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…
Organization
AI-for-Medicine-and-Health
AI-for-Medicine-and-Health
Models in Library1
Datasets in Library1
Models on Hugging Face1
Followers1
Compare the published evidence
This profile connects the 2 model and dataset records shown below to their upstream cards and sources. The library counts describe SAVRN's coverage, rather than this publisher's entire output.
Published tasks: Object detection.
Compare model specifications, source dates, and hardware estimates on the individual records. Publisher identity verification is separate from a model's quality, deployment readiness, or suitability for your work.
Models
Datasets
This repository defines the exact image sets used in PolypRegimeBench, a controlled benchmark of 12 polyp detectors across 6 training regimes. It contains manifests only: file lists, split assignments, filtered IDs, augmentation recipes and checksums. It does not redistribute any third-party endoscopy images, masks or videos. White-light images only. Narrow-band images were excluded so that modality is not confounded with the other factors. Split seed 42, fixed for all runs. Test sets are almost entirely polyp-positive (0, 5 and 0 negative images respectively). The augmentations transform image and mask together: flips, affine (scale, translation, rotation, shear), blur, colour/contrast and…