paper-with-me

홈 › Papers

Self-training with Noisy Student improves ImageNet classification

2019-11-11 · CVPR 2020 6 · Qizhe Xie, Minh-Thang Luong, Eduard Hovy, Quoc V. Le

We present Noisy Student Training, a semi-supervised learning approach that works well even when labeled data is abundant. Noisy Student Training achieves 88.4% top-1 accuracy on ImageNet, which is 2.0% better than the state-of-the-art model that requires 3.5B weakly labeled Instagram images. On robustness test sets, it improves ImageNet-A top-1 accuracy from 61.0% to 83.7%, reduces ImageNet-C mean corruption error from 45.7 to 28.3, and reduces ImageNet-P mean flip rate from 27.8 to 12.2. Noisy Student Training extends the idea of self-training and distillation with the use of equal-or-larger student models and noise added to the student during learning. On ImageNet, we first train an EfficientNet model on labeled images and use it as a teacher to generate pseudo labels for 300M unlabeled images. We then train a larger EfficientNet as a student model on the combination of labeled and pseudo labeled images. We iterate this process by putting back the student as the teacher. During the learning of the student, we inject noise such as dropout, stochastic depth, and data augmentation via RandAugment to the student so that the student generalizes better than the teacher. Models are available at https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet. Code is available at https://github.com/google-research/noisystudent.

📄 PDF Abstract BibTeX arXiv:1911.04252

Code (13)

google-research/noisystudent 공식 구현 tf
tensorflow/tpu 공식 구현 tf
adventure2165/Summarization_self-training_with_noisy_student_improves_imagenet_classification
hamed-ahangari/Separation-Index-of-convolutional-layers-in-EfficientNet-B0 tf
leondgarse/Keras_efficientnet_v2 tf
leondgarse/Keras_efficientnet_v2_test tf
mhd-medfa/NoisyStudent-Based-Object-Recognition tf
phamtrancsek12/offensive-identification pytorch
stanleyjzheng/PyData
tensorflow/tpu/tree/master/models/official/efficientnet tf
thomasly/PaperTranslation
xultaeculcis/coral-net pytorch
yakhyo/EfficientNet-PyTorch pytorch

Tasks

Data AugmentationGeneral ClassificationImage Classification

Methods 이 논문이 사용한 방법론

Test 설명 없음
RMSProp RMSProp is an unpublished adaptive learning rate optimizer proposed by Geoff Hinton. The motivation…
Depthwise Convolution Depthwise Convolution is a type of convolution where we apply a single convolutional filter for each input channel. In the regular 2D…
Pointwise Convolution Pointwise Convolution is a type of convolution that uses a 1x1 kernel: a kernel that iterates through every single point. This…
Depthwise Separable Convolution While standard convolution performs the channelwise and spatial-wise computation in one step, Depthwise Separable Convolution …
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Sigmoid Activation 설명 없음
Batch Normalization 설명 없음

Similar Papers 제목 키워드 기반

Noisy student-teacher training for robust keyword spotting

2021-06-03 · Hyun-Jin Park, Pai Zhu, Ignacio Lopez Moreno, Niranjan Subrahmanya

We propose self-training with noisy student-teacher approach for streaming keyword spotting, that can utilize large-scale unlabeled data and aggressive data augmentation. The proposed method applies aggressive data augme…

Data AugmentationKeyword Spotting

Overcoming Label Ambiguity with Multi-label Iterated Learning

2021-09-29 · Sai Rajeswar Mudumba, Pau Rodriguez, Soumye Singhal, David Vazquez 외

Transfer learning from ImageNet pre-trained models has become essential for many computer vision tasks. Recent studies have shown that ImageNet includes label ambiguity, where images with multiple object classes present …

Multi-Label LearningTransfer Learning

Self-Boosting Vision-Language Models with Noisy Student On-Policy Self-Distillation

2026-07-25 · Shuai Wang, Daoan Zhang, Zhe Tang, Hao Cheng 외 arxiv

Post-training enables vision-language models (VLMs) to understand human instructions and perform various downstream tasks. Current post-training methods usually rely on human-annotated data, distillation from external mo…

Reinforcement LearningVisual Reasoning

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

2021-01-21 · CVPR 2021 1 · Zhaowei Cai, Avinash Ravichandran, Subhransu Maji, Charless Fowlkes 외

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 te…

Self-Supervised LearningSemi-Supervised Image Classification

Improved Noisy Student Training for Automatic Speech Recognition

2020-05-19 · Daniel S. Park, Yu Zhang, Ye Jia, Wei Han 외

Recently, a semi-supervised learning method known as "noisy student training" has been shown to improve image classification performance of deep networks significantly. Noisy student training is an iterative self-trainin…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)image-classificationImage Classification+2