arXiv Machine Learning
CANDOR: Chance-Calibrated Neighborhood Discordance in Frozen Encoders for Medical Imaging
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Jul 22
CANDOR: Chance-Calibrated Discordance in Frozen Foundation Encoders
arXiv:2607. 18451v1 Announce Type: cross Abstract: Frozen encoders are chosen by how well a lightweight head reads a finding from their features, not whether the geometry separates it.
Hugging Face Trending Papers
Jul 20
CANDOR: Chance-Calibrated Discordance in Frozen Foundation Encoders
Frozen encoders are chosen by how well a lightweight head reads a finding from their features, not whether the geometry separates it. Nearest-neighbor discordance does, but with unequal banks the opposite-label neighbor wins on density, not geometry, so prevalence alone makes an uninformed encoder look blind.
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 AI
Sep 24
A Shared Encoder Is Not a Shared Task: Conditional Comparison for Deep Expert Pools
The paper demonstrates that sharing a deep encoder alone does not eliminate the confounding effects in task-comparison scores. By introducing a conditional two‑discriminator discrepancy within the embedding space, the authors achieve robust detection of task changes, maintaining stability under input rotations and accurately tracking label‑permutation drift. This approach, integrated into a mixture‑of‑heads framework, outperforms traditional novelty triggers and generalizes across multiple backbones and datasets, including ImageNet‑21k ViT‑B/16, DINOv2, and CIFAR‑100.
arXiv Computer Vision
3d ago
Representation Risk in Pretrained Image Encoders
arXiv:2609.35470v1 Announce Type: cross Abstract: Applied researchers increasingly convert images into features with pretrained encoders, then use those features in a downstream prediction model. The...
arXiv AI
Sep 24
What Changed? Drift Detection with Real, Virtual, and Incomparable Diagnosis
The paper investigates drift detection in deep learning models, showing that sharing a deep encoder alone does not eliminate confounding in task-comparison scores. By introducing a conditional two‑discriminator discrepancy into the embedding space, the authors create a two‑axis gate that remains stable under input rotations and accurately tracks label‑permutation drift. This approach outperforms traditional exchange or novelty triggers, achieving high AUROC in distinguishing semantic novelty from photometric shift across multiple backbones and datasets.