arXiv Computer Vision
Representation Risk in Pretrained Image Encoders
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Computer Vision
Aug 27
Reliability analysis for BraTS-GoAT segmentation: a controlled robustness study of deep-ensemble uncertainty
The study evaluates the reliability of deep‑ensemble uncertainty for brain tumour segmentation on the BraTS‑GoAT dataset. A 5‑fold cross‑validated nnU‑Net baseline and a 3‑seed deep ensemble were compared for calibration and error detection; the ensemble showed modest gains in calibration on in‑distribution data but the single model’s confidence remained flat while accuracy degraded under synthetic corruptions. Disagreement among ensemble members rose sharply with corruption severity, proving to be a more sensitive indicator of acquisition shift than single‑model confidence.
arXiv Computer Vision
Sep 17
Selective Prediction and Uncertainty-Aware Referral for Pap Smear Classification
arXiv:2609.17545v1 Announce Type: new Abstract: Deep learning models for cervical cytology are almost always evaluated as if every prediction must be acted upon, yet a screening system deployed along...
arXiv AI
Aug 25
CRS-Bench: A Reference-Relative Reliability Benchmark for Medical Image Encoders
arXiv:2608.22059v1 Announce Type: cross Abstract: Pretrained image encoders are central to medical image classification, where expert annotation is costly and task-specific cohorts are often limited....
arXiv AI
Sep 25
Med-AR: Autoregressive Vision-Language Pretraining for Long-Tailed Chest X-Ray Classification and Uncertainty-Aware Evaluation
Med-AR introduces two autoregressive vision‑language models, Med‑AR‑8B and Med‑AR‑2B, pretrained on structured radiology reports, abnormality‑focused text, and region annotations to address long‑tailed chest X‑ray classification. The models outperform existing contrastive, self‑supervised, and supervised encoders—including Med‑CLIP, CheXFound, EVA‑Base, ARK, and BioViL‑T—across PadChest, MIMIC‑CXR, and CheXpert, achieving higher mean AUROC and AUPRC for head, medium, and tail findings and lower excess area under the risk‑coverage curve. Med‑AR also demonstrates improved selective‑prediction performance, with Med‑AR‑8B raising tail‑label mean AUPRC on MIMIC‑CXR from 0.1033 to 0.1441 and Med‑AR‑2B delivering the strongest discrimination on PadChest.
arXiv AI
Aug 18
Picking the Right Image to Classify: Reliable-Input Selection in Teledermatology
arXiv:2608. 16198v1 Announce Type: cross Abstract: Dermatology models face distribution shifts in teledermatology settings, where submitted images differ from the training data in lighting, angle, distance, focus, and framing.
arXiv Machine Learning
Sep 22
CANDOR: Chance-Calibrated Neighborhood Discordance in Frozen Encoders for Medical Imaging
arXiv:2607.18451v3 Announce Type: replace Abstract: A foundation encoder is pretrained once on a large image corpus and then reused with its weights frozen. Each new task is solved by training a smal...