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

• URL: http://arxiv.org/abs/2302.10586v3
• Date: Tue, 31 Oct 2023 11:38:08 GMT
• Title: Diffusion Models and Semi-Supervised Learners Benefit Mutually with Few Labels
• Authors: Zebin You, Yong Zhong, Fan Bao, Jiacheng Sun, Chongxuan Li, Jun Zhu
• Abstract summary: We propose a simple yet effective training strategy called dual pseudo training (DPT) 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. 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.
• Score: 47.15381781274115
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Beyond the Label Itself: Latent Labels Enhance Semi-supervised Point Cloud Panoptic Segmentation [46.01433705072047]
  We find two types of latent labels behind the displayed label embedded in LiDAR and image data. We propose a novel augmentation, Cylinder-Mix, which is able to augment more yet reliable samples for training. We also propose the Instance Position-scale Learning (IPSL) Module to learn and fuse the information of instance position and scale.
  arXiv  Detail & Related papers  (2023-12-13T15:56:24Z)
• A Semi-Paired Approach For Label-to-Image Translation [6.888253564585197]
  We introduce the first semi-supervised (semi-paired) framework for label-to-image translation. In the semi-paired setting, the model has access to a small set of paired data and a larger set of unpaired images and labels. We propose a training algorithm for this shared network, and we present a rare classes sampling algorithm to focus on under-represented classes.
  arXiv  Detail & Related papers  (2023-06-23T16:13:43Z)
• Pseudo Labels for Single Positive Multi-Label Learning [0.0]
  Single positive multi-label (SPML) learning is a cost-effective solution, where models are trained on a single positive label per image. In this work, we propose a method to turn single positive data into fully-labeled data: Pseudo Multi-Labels.
  arXiv  Detail & Related papers  (2023-06-01T17:21:42Z)
• NP-Match: Towards a New Probabilistic Model for Semi-Supervised Learning [86.60013228560452]
  Semi-supervised learning (SSL) has been widely explored in recent years, and it is an effective way of leveraging unlabeled data. In this work, we adjust neural processes (NPs) to the semi-supervised image classification task, resulting in a new method named NP-Match. NP-Match implicitly compares data points when making predictions, and as a result, the prediction of each unlabeled data point is affected by the labeled data points.
  arXiv  Detail & Related papers  (2023-01-31T11:44:45Z)
• Mix-Teaching: A Simple, Unified and Effective Semi-Supervised Learning Framework for Monocular 3D Object Detection [22.074959519526605]
  Mix-Teaching is an effective semi-supervised learning framework applicable to employ both labeled and unlabeled images in training stage. Mix-Teaching consistently improves MonoFlex and GUPNet by significant margins under various labeling ratios on KITTI dataset.
  arXiv  Detail & Related papers  (2022-07-10T12:07:25Z)
• Masked Unsupervised Self-training for Zero-shot Image Classification [98.23094305347709]
  Masked Unsupervised Self-Training (MUST) is a new approach which leverages two different and complimentary sources of supervision: pseudo-labels and raw images. MUST improves upon CLIP by a large margin and narrows the performance gap between unsupervised and supervised classification.
  arXiv  Detail & Related papers  (2022-06-07T02:03:06Z)
• Semi-Supervised Domain Adaptation with Prototypical Alignment and Consistency Learning [86.6929930921905]
  This paper studies how much it can help address domain shifts if we further have a few target samples labeled. To explore the full potential of landmarks, we incorporate a prototypical alignment (PA) module which calculates a target prototype for each class from the landmarks. Specifically, we severely perturb the labeled images, making PA non-trivial to achieve and thus promoting model generalizability.
  arXiv  Detail & Related papers  (2021-04-19T08:46:08Z)
• An Empirical Study of the Collapsing Problem in Semi-Supervised 2D Human Pose Estimation [80.02124918255059]
  Semi-supervised learning aims to boost the accuracy of a model by exploring unlabeled images. We learn two networks to mutually teach each other. The more reliable predictions on easy images in each network are used to teach the other network to learn about the corresponding hard images.
  arXiv  Detail & Related papers  (2020-11-25T03:29:52Z)
• Big Self-Supervised Models are Strong Semi-Supervised Learners [116.00752519907725]
  We show that it is surprisingly effective for semi-supervised learning on ImageNet. A key ingredient of our approach is the use of big (deep and wide) networks during pretraining and fine-tuning. We find that, the fewer the labels, the more this approach (task-agnostic use of unlabeled data) benefits from a bigger network.
  arXiv  Detail & Related papers  (2020-06-17T17:48:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.