Exponential Moving Average Normalization for Self-supervised and Semi-supervised Learning

• URL: http://arxiv.org/abs/2101.08482v1
• Date: Thu, 21 Jan 2021 07:45:37 GMT
• Title: Exponential Moving Average Normalization for Self-supervised and Semi-supervised Learning
• Abstract summary: We present a plug-in replacement for batch normalization (BN) called exponential moving average normalization (EMAN) Unlike the standard BN, where the statistics are computed within each batch, EMAN, used in the teacher, updates its statistics by exponential moving average from the BN statistics of the student. EMAN improves strong baselines for self-supervised learning by 4-6/1-2 points and semi-supervised learning by about 7/2 points, when 1%/10% supervised labels are available on ImageNet.
• Score: 90.69256802784689
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present a plug-in replacement for batch normalization (BN) called exponential moving average normalization (EMAN), which improves the performance of existing student-teacher based self- and semi-supervised learning techniques. Unlike the standard BN, where the statistics are computed within each batch, EMAN, used in the teacher, updates its statistics by exponential moving average from the BN statistics of the student. This design reduces the intrinsic cross-sample dependency of BN and enhance the generalization of the teacher. EMAN improves strong baselines for self-supervised learning by 4-6/1-2 points and semi-supervised learning by about 7/2 points, when 1%/10% supervised labels are available on ImageNet. These improvements are consistent across methods, network architectures, training duration, and datasets, demonstrating the general effectiveness of this technique.

Related papers

• Hybrid Batch Normalisation: Resolving the Dilemma of Batch Normalisation in Federated Learning [34.07540860626276]
  Batch Normalisation (BN) is widely used in deep neural network training to harmonise the input-output distributions for each batch of data.<n>In this work, we develop a customised normalisation approach, Hybrid Batch Normalisation (HBN)<n>HBN separates the update of statistical parameters from that of learnable parameters, obtaining unbiased estimates of global statistical parameters in distributed scenarios.
  arXiv  Detail & Related papers  (2025-05-28T01:46:34Z)
• PRISM: Self-Pruning Intrinsic Selection Method for Training-Free Multimodal Data Selection [68.8373788348678]
  Visual instruction tuning adapts pre-trained Multimodal Large Language Models to follow human instructions.<n>PRISM is the first training-free framework for efficient visual instruction selection.<n>It reduces the end-to-end time for data selection and model tuning to just 30% of conventional pipelines.
  arXiv  Detail & Related papers  (2025-02-17T18:43:41Z)
• Unified Batch Normalization: Identifying and Alleviating the Feature Condensation in Batch Normalization and a Unified Framework [55.22949690864962]
  Batch Normalization (BN) has become an essential technique in contemporary neural network design. We propose a two-stage unified framework called Unified Batch Normalization (UBN) UBN significantly enhances performance across different visual backbones and different vision tasks.
  arXiv  Detail & Related papers  (2023-11-27T16:41:31Z)
• Overcoming Recency Bias of Normalization Statistics in Continual Learning: Balance and Adaptation [67.77048565738728]
  Continual learning involves learning a sequence of tasks and balancing their knowledge appropriately. We propose Adaptive Balance of BN (AdaB$2$N), which incorporates appropriately a Bayesian-based strategy to adapt task-wise contributions. Our approach achieves significant performance gains across a wide range of benchmarks.
  arXiv  Detail & Related papers  (2023-10-13T04:50:40Z)
• TWINS: A Fine-Tuning Framework for Improved Transferability of Adversarial Robustness and Generalization [89.54947228958494]
  This paper focuses on the fine-tuning of an adversarially pre-trained model in various classification tasks. We propose a novel statistics-based approach, Two-WIng NormliSation (TWINS) fine-tuning framework. TWINS is shown to be effective on a wide range of image classification datasets in terms of both generalization and robustness.
  arXiv  Detail & Related papers  (2023-03-20T14:12:55Z)
• Context Normalization Layer with Applications [0.1499944454332829]
  This study proposes a new normalization technique, called context normalization, for image data. It adjusts the scaling of features based on the characteristics of each sample, which improves the model's convergence speed and performance. The effectiveness of context normalization is demonstrated on various datasets, and its performance is compared to other standard normalization techniques.
  arXiv  Detail & Related papers  (2023-03-14T06:38:17Z)
• Kaizen: Continuously improving teacher using Exponential Moving Average for semi-supervised speech recognition [41.78509185887238]
  The proposed approach uses a teacher model which is updated as the exponential moving average of the student model parameters. The proposed approach shows more than 10% word error rate (WER) reduction over standard teacher-student training.
  arXiv  Detail & Related papers  (2021-06-14T21:15:36Z)
• Unbiased Teacher for Semi-Supervised Object Detection [50.0087227400306]
  We revisit the Semi-Supervised Object Detection (SS-OD) and identify the pseudo-labeling bias issue in SS-OD. We introduce Unbiased Teacher, a simple yet effective approach that jointly trains a student and a gradually progressing teacher in a mutually-beneficial manner.
  arXiv  Detail & Related papers  (2021-02-18T17:02:57Z)
• Robust Disentanglement of a Few Factors at a Time [5.156484100374058]
  We introduce population-based training (PBT) for improving consistency in training variational autoencoders (VAEs) We then use Unsupervised Disentanglement Ranking (UDR) as an unsupervised to score models in our PBT-VAE training and show how models trained this way tend to consistently disentangle only a subset of the generative factors. We show striking improvement in state-of-the-art unsupervised disentanglement performance and robustness across multiple datasets and metrics.
  arXiv  Detail & Related papers  (2020-10-26T12:34:23Z)
• Double Forward Propagation for Memorized Batch Normalization [68.34268180871416]
  Batch Normalization (BN) has been a standard component in designing deep neural networks (DNNs) We propose a memorized batch normalization (MBN) which considers multiple recent batches to obtain more accurate and robust statistics. Compared to related methods, the proposed MBN exhibits consistent behaviors in both training and inference.
  arXiv  Detail & Related papers  (2020-10-10T08:48:41Z)

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.