# JDCNet: Confidence-Gated Privileged-Modality Distillation for Cost-Preserving X-ray Inference

arXiv: https://arxiv.org/abs/2603.29167 · HTML: https://mlsanity.com/paper/2603.29167/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Distillation for medical imaging, one of 12 directions in Knowledge distillation.
- Builds on 27 of its 36 references that are in the map.
- First posted on arXiv 31 Mar 2026.

## Placed in

- Knowledge distillation / [Distillation for medical imaging](https://mlsanity.com/distill/distillation-for-medical-imaging/)

## Builds on (most cited first, 27 of 27)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison](https://mlsanity.com/paper/1901.07031/) (2019)
- [Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer](https://mlsanity.com/paper/1612.03928/) (2016)
- [Contrastive Representation Distillation](https://mlsanity.com/paper/1910.10699/) (2019)
- [BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs](https://mlsanity.com/paper/2303.00915/) (2023)
- [CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning](https://mlsanity.com/paper/1711.05225/) (2017)
- [Confounding variables can degrade generalization performance of radiological deep learning models](https://mlsanity.com/paper/1807.00431/) (2018)
- [Transfusion: Understanding Transfer Learning for Medical Imaging](https://mlsanity.com/paper/1902.07208/) (2019)
- [Unifying distillation and privileged information](https://mlsanity.com/paper/1511.03643/) (2015)
- [Hidden Stratification Causes Clinically Meaningful Failures in Machine Learning for Medical Imaging](https://mlsanity.com/paper/1909.12475/) (2019)
- [Cross Modal Distillation for Supervision Transfer](https://mlsanity.com/paper/1507.00448/) (2015)
- [Common pitfalls and recommendations for using machine learning to detect and prognosticate for COVID-19 using chest radiographs and CT scans](https://mlsanity.com/paper/2008.06388/) (2020)
- [Why rankings of biomedical image analysis competitions should be interpreted with care](https://mlsanity.com/paper/1806.02051/) (2018)
- [Soft-Label Anonymous Gastric X-ray Image Distillation](https://mlsanity.com/paper/2104.02857/) (2021)
- [How I failed machine learning in medical imaging -- shortcomings and recommendations](https://mlsanity.com/paper/2103.10292/) (2021)
- [XKD: Cross-modal Knowledge Distillation with Domain Alignment for Video Representation Learning](https://mlsanity.com/paper/2211.13929/) (2022)
- [COVID-VIT: Classification of COVID-19 from CT chest images based on vision transformer models](https://mlsanity.com/paper/2107.01682/) (2021)
- [Quantifying the Knowledge in GNNs for Reliable Distillation into MLPs](https://mlsanity.com/paper/2306.05628/) (2023)
- [Multi-modal Vision Pre-training for Medical Image Analysis](https://mlsanity.com/paper/2410.10604/) (2024)
- [Variational Knowledge Distillation for Disease Classification in Chest X-Rays](https://mlsanity.com/paper/2103.10825/) (2021)
- [BD-KD: Balancing the Divergences for Online Knowledge Distillation](https://mlsanity.com/paper/2212.12965/) (2022)
- [MST-Distill: Mixture of Specialized Teachers for Cross-Modal Knowledge Distillation](https://mlsanity.com/paper/2507.07015/) (2025)
- [Revisiting Cross-Modal Knowledge Distillation: A Disentanglement Approach for RGBD Semantic Segmentation](https://mlsanity.com/paper/2505.24361/) (2025)

## Abstract (arXiv)

We study a systems-level visual inference problem: using an expensive privileged modality during training while preserving a fixed-cost, single-modality deployment path. We present JDCNet, a confidence-gated CT-to-X-ray distillation framework in which the CT teacher supplies an auxiliary hard or temperature-scaled target only on training samples whose teacher confidence exceeds a threshold; at deployment the student takes X-ray input alone and matches the parameter, MAC, and latency profile of the supervised X-ray baseline. On a 510-patient same-patient paired BIMCV cohort with patient-level 5-fold cross-validation, two JDCNet configurations clear a fixed transfer gate against the supervised ResNet-18 baseline: 3-slice soft-KL supervision yields DeltaBA=+0.035 (95% CI [+0.011,+0.057]) and mid-slice hard supervision yields +0.033 ([+0.007,+0.058]). Under the same splits and gate, logit distillation, gated logit distillation, contrastive alignment, attention transfer, feature hints, BiomedCLIP fine-tuning, and a module-augmented variant do not pass. Confidence-gated auxiliary targets are therefore a more transferable channel than uniformly softened CT logits; the evidence is bounded to one paired cohort, so external paired-cohort replication is required before any deployment claim.