VCC-INFUSE: Towards Accurate and Efficient Selection of Unlabeled Examples in Semi-supervised Learning

• URL: http://arxiv.org/abs/2404.11947v2
• Date: Sun, 21 Apr 2024 06:36:08 GMT
• Title: VCC-INFUSE: Towards Accurate and Efficient Selection of Unlabeled Examples in Semi-supervised Learning
• Authors: Shijie Fang, Qianhan Feng, Tong Lin,
• Abstract summary: Existing methods fail to utilize unlabeled data effectively and efficiently. We propose two methods: Variational Confidence (VCC) and Influence-Function-based Unlabeled Sample Elimination (INFUSE) Our methods are effective in multiple datasets and settings, reducing errors classification rates and saving training time.
• Score: 1.0007051676618415
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Despite the progress of Semi-supervised Learning (SSL), existing methods fail to utilize unlabeled data effectively and efficiently. Many pseudo-label-based methods select unlabeled examples based on inaccurate confidence scores from the classifier. Most prior work also uses all available unlabeled data without pruning, making it difficult to handle large amounts of unlabeled data. To address these issues, we propose two methods: Variational Confidence Calibration (VCC) and Influence-Function-based Unlabeled Sample Elimination (INFUSE). VCC is an universal plugin for SSL confidence calibration, using a variational autoencoder to select more accurate pseudo labels based on three types of consistency scores. INFUSE is a data pruning method that constructs a core dataset of unlabeled examples under SSL. Our methods are effective in multiple datasets and settings, reducing classification errors rates and saving training time. Together, VCC-INFUSE reduces the error rate of FlexMatch on the CIFAR-100 dataset by 1.08% while saving nearly half of the training time.

Related papers

• FlatMatch: Bridging Labeled Data and Unlabeled Data with Cross-Sharpness for Semi-Supervised Learning [73.13448439554497]
  Semi-Supervised Learning (SSL) has been an effective way to leverage abundant unlabeled data with extremely scarce labeled data. Most SSL methods are commonly based on instance-wise consistency between different data transformations. We propose FlatMatch which minimizes a cross-sharpness measure to ensure consistent learning performance between the two datasets.
  arXiv  Detail & Related papers  (2023-10-25T06:57:59Z)
• Boosting Semi-Supervised Learning by bridging high and low-confidence predictions [4.18804572788063]
  Pseudo-labeling is a crucial technique in semi-supervised learning (SSL) We propose a new method called ReFixMatch, which aims to utilize all of the unlabeled data during training.
  arXiv  Detail & Related papers  (2023-08-15T00:27:18Z)
• Soft Curriculum for Learning Conditional GANs with Noisy-Labeled and Uncurated Unlabeled Data [70.25049762295193]
  We introduce a novel conditional image generation framework that accepts noisy-labeled and uncurated data during training. We propose soft curriculum learning, which assigns instance-wise weights for adversarial training while assigning new labels for unlabeled data. Our experiments show that our approach outperforms existing semi-supervised and label-noise robust methods in terms of both quantitative and qualitative performance.
  arXiv  Detail & Related papers  (2023-07-17T08:31:59Z)
• Boosting Semi-Supervised Learning with Contrastive Complementary Labeling [11.851898765002334]
  A popular approach is pseudo-labeling that generates pseudo labels only for those unlabeled data with high-confidence predictions. We highlight that data with low-confidence pseudo labels can be still beneficial to the training process. Inspired by this, we propose a novel Contrastive Complementary Labeling (CCL) method that constructs a large number of reliable negative pairs.
  arXiv  Detail & Related papers  (2022-12-13T15:25:49Z)
• Dash: Semi-Supervised Learning with Dynamic Thresholding [72.74339790209531]
  We propose a semi-supervised learning (SSL) approach that uses unlabeled examples to train models. Our proposed approach, Dash, enjoys its adaptivity in terms of unlabeled data selection.
  arXiv  Detail & Related papers  (2021-09-01T23:52:29Z)
• OpenCoS: Contrastive Semi-supervised Learning for Handling Open-set Unlabeled Data [65.19205979542305]
  Unlabeled data may include out-of-class samples in practice. OpenCoS is a method for handling this realistic semi-supervised learning scenario.
  arXiv  Detail & Related papers  (2021-06-29T06:10:05Z)
• OpenMatch: Open-set Consistency Regularization for Semi-supervised Learning with Outliers [71.08167292329028]
  We propose a novel Open-set Semi-Supervised Learning (OSSL) approach called OpenMatch. OpenMatch unifies FixMatch with novelty detection based on one-vs-all (OVA) classifiers. It achieves state-of-the-art performance on three datasets, and even outperforms a fully supervised model in detecting outliers unseen in unlabeled data on CIFAR10.
  arXiv  Detail & Related papers  (2021-05-28T23:57:15Z)
• In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning [53.1047775185362]
  Pseudo-labeling (PL) is a general SSL approach that does not have this constraint but performs relatively poorly in its original formulation. We argue that PL underperforms due to the erroneous high confidence predictions from poorly calibrated models. We propose an uncertainty-aware pseudo-label selection (UPS) framework which improves pseudo labeling accuracy by drastically reducing the amount of noise encountered in the training process.
  arXiv  Detail & Related papers  (2021-01-15T23:29:57Z)

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.