← Back to all news
arXiv Machine Learning By Qinyu Li, Yee Whye Teh, Chris Holmes, Joel Jaskari

Data-Efficient Classifier Pretraining Through Diffusion Models

Read the original on arXiv Machine Learning →

The paper introduces DiffPT, a diffusion‑based pretraining method for classifier backbones aimed at improving performance when training data is scarce. Experiments on time‑series, natural image, and medical imaging datasets show that DiffPT outperforms many self‑supervised baselines, especially in low‑data regimes for medical and time‑series tasks. While contrastive pretraining remains superior on CIFAR‑10 and Tiny ImageNet, DiffPT offers a simple and effective alternative across diverse modalities.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Jul 15

Steering Diffusion Models via Class-Contrastive Influence for Few-Shot Medical Classification

arXiv:2607. 12464v1 Announce Type: cross Abstract: When labeled data are scarce, off-the-shelf diffusion models can augment training sets for few-shot medical image classification, but not all generated samples are equally useful for the downstream task.

By Jeeyung Kim, Erfan Esmaeili, Qiang Qiu
diffusioncomputer-visionreinforcement-learningfine-tuningbenchmarks
More like this →
arXiv Machine Learning
Sep 10

Large-Scale Pretraining for Improving Deep Learning-Based Geometric Distortion Correction of Diffusion-Weighted Imaging

The paper explores large‑scale pretraining to enhance deep learning‑based geometric distortion correction for diffusion‑weighted imaging (DWI). By framing the task as image reconstruction, the authors compare a non‑pretrained baseline with self‑supervised and generative pretrained models, finding that the cWDM model yields the best quantitative and qualitative results. When applied to low‑resource, high‑throughput settings in a low‑ and middle‑income country, the pretrained models faced transferability issues, but aligning images to a common standard space improved predictions, indicating that harmonized preprocessing can aid cross‑domain deployment.

By Saroj Khanal, Yashawant Kumar Yadav, Kritam Bhattarai, Jeevan Neupane, Shristi Subedi, Saship Gwachha, Manish Kumar Tiwari, Dong Zhang, Confidence Raymond, Aondona Moses Iorumbur, Udunna Anazodo, Surendra Maharjan, Bishesh Khanal, Mahesh Shakya, Pralhad Kumar Shrestha
diffusionefficiency
More like this →
arXiv AI
Aug 24

Consistency Models for Fast MRI Reconstruction Using Regularization by Denoising

The paper introduces CM-RED, a fast MRI reconstruction method that combines a pretrained consistency model with the regularization by denoising framework. By integrating controlled noise injection into accelerated proximal gradient updates, CM-RED achieves high‑quality reconstructions on fastMRI knee and brain datasets with only four network function evaluations. It consistently outperforms existing diffusion‑ and consistency‑based approaches in quantitative metrics, visual fidelity, and robustness to hyperparameter changes.

By Merve G\"ulle, Junno Yun, Ya\c{s}ar Utku Al\c{c}alar, Mehmet Ak\c{c}akaya
diffusion
More like this →