paper-with-me

Papers

Diffusion Models and Semi-Supervised Learners Benefit Mutually with Few Labels

2023-02-21 · NeurIPS 2023 11 · Zebin You, Yong Zhong, Fan Bao, Jiacheng Sun, Chongxuan Li, Jun Zhu

In an effort to further advance semi-supervised generative and classification tasks, we propose a simple yet effective training strategy called dual pseudo training (DPT), built upon strong semi-supervised learners and diffusion models. DPT operates in three stages: training a classifier on partially labeled data to predict pseudo-labels; training a conditional generative model using these pseudo-labels to generate pseudo images; and retraining the classifier with a mix of real and pseudo images. Empirically, DPT consistently achieves SOTA performance of semi-supervised generation and classification across various settings. In particular, with one or two labels per class, DPT achieves a Fr\'echet Inception Distance (FID) score of 3.08 or 2.52 on ImageNet 256x256. Besides, DPT outperforms competitive semi-supervised baselines substantially on ImageNet classification tasks, achieving top-1 accuracies of 59.0 (+2.8), 69.5 (+3.0), and 74.4 (+2.0) with one, two, or five labels per class, respectively. Notably, our results demonstrate that diffusion can generate realistic images with only a few labels (e.g., <0.1%) and generative augmentation remains viable for semi-supervised classification. Our code is available at https://github.com/ML-GSAI/DPT.

📄 PDF Abstract BibTeX arXiv:2302.10586

Code (3)

baofff/U-ViT 공식 구현 pytorch
ml-gsai/dpt 공식 구현 pytorch
MindCode-4/code-3/tree/main/dpt mindspore

Tasks

Classification

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Six Ways To Communicate To Someone At Expedia Via Phone And Email's. To communicate or get human at Expedia, the quickest option is typically to call their customer service at +1-888-829-0881 or +1(805) 330 (4056). You can also use the live chat…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Residual Connection 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Similar Papers 제목 키워드 기반

DDAE++: Enhancing Diffusion Models Towards Unified Generative and Discriminative Learning

2025-05-16 · Weilai Xiang, Hongyu Yang, Di Huang, Yunhong Wang

While diffusion models have gained prominence in image synthesis, their generative pre-training has been shown to yield discriminative representations, paving the way towards unified visual generation and understanding. …

DenoisingImage Generation

Diffusion-Scheduled Denoising Autoencoders for Anomaly Detection in Tabular Data

2025-08-01 · Timur Sattarov, Marco Schreyer, Damian Borth arxiv

Anomaly detection in tabular data remains challenging due to complex feature interactions and the scarcity of anomalous examples. Denoising autoencoders rely on fixed-magnitude noise, limiting adaptability to diverse dat…

Contrastive LearningAnomaly Detection

More Photos are All You Need: Semi-Supervised Learning for Fine-Grained Sketch Based Image Retrieval

2021-03-25 · CVPR 2021 1 · Ayan Kumar Bhunia, Pinaki Nath Chowdhury, Aneeshan Sain, Yongxin Yang 외

A fundamental challenge faced by existing Fine-Grained Sketch-Based Image Retrieval (FG-SBIR) models is the data scarcity -- model performances are largely bottlenecked by the lack of sketch-photo pairs. Whilst the numbe…

AllCross-Modal RetrievalImage RetrievalRetrieval+2

Big Self-Supervised Models are Strong Semi-Supervised Learners

2020-06-17 · NeurIPS 2020 12 · Ting Chen, Simon Kornblith, Kevin Swersky, Mohammad Norouzi 외

One paradigm for learning from few labeled examples while making best use of a large amount of unlabeled data is unsupervised pretraining followed by supervised fine-tuning. Although this paradigm uses unlabeled data in …

Self-Supervised Image ClassificationSemi-Supervised Image Classification

Leveraging Out-of-Distribution Unlabeled Images: Semi-Supervised Semantic Segmentation with an Open-Vocabulary Model

2025-07-04 · WooSeok Shin, Jisu Kang, Hyeonki Jeong, Jin Sob Kim 외

In semi-supervised semantic segmentation, existing studies have shown promising results in academic settings with controlled splits of benchmark datasets. However, the potential benefits of leveraging significantly large…

Pseudo LabelSegmentationSemantic SegmentationSemi-Supervised Semantic Segmentation