# Prompt-Driven Feature Diffusion for Open-World Semi-Supervised Learning

arXiv: https://arxiv.org/abs/2404.11795 · HTML: https://mlsanity.com/paper/2404.11795/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models.
- Builds on 26 of its 36 references that are in the map.
- First posted on arXiv 17 Apr 2024.

## Placed in

- Diffusion models / [Image generation, text-to-image and editing](https://mlsanity.com/diffusion/image-generation-text-to-image-and-editing/)

## Builds on (most cited first, 26 of 26)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [MixMatch: A Holistic Approach to Semi-Supervised Learning](https://mlsanity.com/paper/1905.02249/) (2019)
- [Diffusion Models: A Comprehensive Survey of Methods and Applications](https://mlsanity.com/paper/2209.00796/) (2022)
- [Temporal Ensembling for Semi-Supervised Learning](https://mlsanity.com/paper/1610.02242/) (2016)
- [Understanding Diffusion Models: A Unified Perspective](https://mlsanity.com/paper/2208.11970/) (2022)
- [Your Diffusion Model is Secretly a Zero-Shot Classifier](https://mlsanity.com/paper/2303.16203/) (2023)
- [Towards Open World Recognition](https://mlsanity.com/paper/1412.5687/) (2014)
- [Learning to Discover Novel Visual Categories via Deep Transfer Clustering](https://mlsanity.com/paper/1908.09884/) (2019)
- [Open-World Semi-Supervised Learning](https://mlsanity.com/paper/2102.03526/) (2021)
- [A Unified Objective for Novel Class Discovery](https://mlsanity.com/paper/2108.08536/) (2021)
- [Automatically Discovering and Learning New Visual Categories with Ranking Statistics](https://mlsanity.com/paper/2002.05714/) (2020)
- [Text-to-Image Diffusion Models are Zero-Shot Classifiers](https://mlsanity.com/paper/2303.15233/) (2023)
- [Learning to cluster in order to transfer across domains and tasks](https://mlsanity.com/paper/1711.10125/) (2017)
- [Conditional Gaussian Distribution Learning for Open Set Recognition](https://mlsanity.com/paper/2003.08823/) (2020)
- [Diffusion Models and Semi-Supervised Learners Benefit Mutually with Few Labels](https://mlsanity.com/paper/2302.10586/) (2023)
- [ProtoDiff: Learning to Learn Prototypical Networks by Task-Guided Diffusion](https://mlsanity.com/paper/2306.14770/) (2023)
- [Diffusion-SS3D: Diffusion Model for Semi-supervised 3D Object Detection](https://mlsanity.com/paper/2312.02966/) (2023)

## Abstract (arXiv)

In this paper, we present a novel approach termed Prompt-Driven Feature Diffusion (PDFD) within a semi-supervised learning framework for Open World Semi-Supervised Learning (OW-SSL). At its core, PDFD deploys an efficient feature-level diffusion model with the guidance of class-specific prompts to support discriminative feature representation learning and feature generation, tackling the challenge of the non-availability of labeled data for unseen classes in OW-SSL. In particular, PDFD utilizes class prototypes as prompts in the diffusion model, leveraging their class-discriminative and semantic generalization ability to condition and guide the diffusion process across all the seen and unseen classes. Furthermore, PDFD incorporates a class-conditional adversarial loss for diffusion model training, ensuring that the features generated via the diffusion process can be discriminatively aligned with the class-conditional features of the real data. Additionally, the class prototypes of the unseen classes are computed using only unlabeled instances with confident predictions within a semi-supervised learning framework. We conduct extensive experiments to evaluate the proposed PDFD. The empirical results show PDFD exhibits remarkable performance enhancements over many state-of-the-art existing methods.