TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Papers/OCD: Learning to Overfit with Conditional Diffusion Models

OCD: Learning to Overfit with Conditional Diffusion Models

Shahar Lutati, Lior Wolf

2022-10-02DenoisingImage ClassificationSpeech Separation3D ReconstructionFew-Shot Text Classification
PaperPDFCode(official)

Abstract

We present a dynamic model in which the weights are conditioned on an input sample x and are learned to match those that would be obtained by finetuning a base model on x and its label y. This mapping between an input sample and network weights is approximated by a denoising diffusion model. The diffusion model we employ focuses on modifying a single layer of the base model and is conditioned on the input, activations, and output of this layer. Since the diffusion model is stochastic in nature, multiple initializations generate different networks, forming an ensemble, which leads to further improvements. Our experiments demonstrate the wide applicability of the method for image classification, 3D reconstruction, tabular data, speech separation, and natural language processing. Our code is available at https://github.com/ShaharLutatiPersonal/OCD

Results

TaskDatasetMetricValueModel
Speech SeparationLibri5MixSI-SDRi13.4OCD
Text ClassificationSST-5Accuracy0.478SetFit + OCD
Text ClassificationAverage on NLP datasetsAccuracy0.648SetFit + OCD(5)
Text ClassificationAverage on NLP datasetsAccuracy0.643SetFit + OCD
Text ClassificationAverage on NLP datasetsAccuracy0.633T-few 3B
Text ClassificationAverage on NLP datasetsAccuracy0.622SetFit
Text ClassificationAmazon CounterfeitAccuracy0.41SetFit + OCD
Few-Shot Text ClassificationSST-5Accuracy0.478SetFit + OCD
Few-Shot Text ClassificationAverage on NLP datasetsAccuracy0.648SetFit + OCD(5)
Few-Shot Text ClassificationAverage on NLP datasetsAccuracy0.643SetFit + OCD
Few-Shot Text ClassificationAverage on NLP datasetsAccuracy0.633T-few 3B
Few-Shot Text ClassificationAverage on NLP datasetsAccuracy0.622SetFit
Few-Shot Text ClassificationAmazon CounterfeitAccuracy0.41SetFit + OCD
ClassificationSST-5Accuracy0.478SetFit + OCD
ClassificationAverage on NLP datasetsAccuracy0.648SetFit + OCD(5)
ClassificationAverage on NLP datasetsAccuracy0.643SetFit + OCD
ClassificationAverage on NLP datasetsAccuracy0.633T-few 3B
ClassificationAverage on NLP datasetsAccuracy0.622SetFit
ClassificationAmazon CounterfeitAccuracy0.41SetFit + OCD

Related Papers

Automatic Classification and Segmentation of Tunnel Cracks Based on Deep Learning and Visual Explanations2025-07-18fastWDM3D: Fast and Accurate 3D Healthy Tissue Inpainting2025-07-17Diffuman4D: 4D Consistent Human View Synthesis from Sparse-View Videos with Spatio-Temporal Diffusion Models2025-07-17Adversarial attacks to image classification systems using evolutionary algorithms2025-07-17Efficient Adaptation of Pre-trained Vision Transformer underpinned by Approximately Orthogonal Fine-Tuning Strategy2025-07-17Federated Learning for Commercial Image Sources2025-07-17MUPAX: Multidimensional Problem Agnostic eXplainable AI2025-07-17AutoPartGen: Autogressive 3D Part Generation and Discovery2025-07-17