Semi-Supervised Segmentation of Salt Bodies in Seismic Images using an Ensemble of Convolutional Neural Networks

Babakhin, Yauhen; Sanakoyeu, Artsiom; Kitamura, Hirotoshi

doi:10.48550/arxiv.1904.04445

Cited by 3 publications

(2 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Self-training / co-training has also been shown to work well for a variety of other tasks including leveraging noisy data [81], semantic segmentation [4], text classification [38,73]. Back translation has led to significant improvements in machine translation [67,19,27,13].…”

Section: Related Workmentioning

confidence: 99%

Self-training with Noisy Student improves ImageNet classification

Xie

Luong

Hovy

et al. 2019

Preprint

119

159

View full text Add to dashboard Cite

We present a simple self-training method that 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.To achieve this result, we first train an EfficientNet model on labeled ImageNet images and use it as a teacher to generate pseudo labels on 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 generation of the pseudo labels, the teacher is not noised so that the pseudo labels are as accurate as possible. However, 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.

show abstract

Section: Related Workmentioning

confidence: 99%

Self-training with Noisy Student improves ImageNet classification

Xie

Luong

Hovy

et al. 2019

Preprint

119

159

View full text Add to dashboard Cite

show abstract

“…We noticed by visual inspection that the training set of GLD v1 is clean and reliable, so we used the dataset as is for training. To obtain a semi-supervised learning effect [4,23], we added virtual classes to the training set. These virtual classes are the clusters from the test and index sets of GLD v1.…”

Section: Dataset Cleaning For Trainingmentioning

confidence: 99%

A Benchmark on Tricks for Large-scale Image Retrieval

Ko¹,

Shin²,

Gu³

et al. 2019

Preprint

View full text Add to dashboard Cite

Many studies have been performed on metric learning, which has become a key ingredient in top-performing methods of instance-level image retrieval. Meanwhile, less attention has been paid to pre-processing and post-processing tricks that can significantly boost performance. Furthermore, we found that most previous studies used small scale datasets to simplify processing. Because the behavior of a feature representation in a deep learning model depends on both domain and data, it is important to understand how model behave in large-scale environments when a proper combination of retrieval tricks is used. In this paper, we extensively analyze the effect of well-known pre-processing, post-processing tricks, and their combination for largescale image retrieval. We found that proper use of these tricks can significantly improve model performance without necessitating complex architecture or introducing loss, as confirmed by achieving a competitive result on the Google Landmark Retrieval Challenge 2019.

show abstract

Semi-Supervised Wide-Angle Portraits Correction by Multi-Scale Transformer

Zhu¹,

Shu²,

Wang³

et al. 2021

Preprint

View full text Add to dashboard Cite

We propose a semi-supervised network for wide-angle portraits correction. Wide-angle images often suffer from skew and distortion affected by perspective distortion, especially noticeable at the face regions. Previous deep learning based approaches require the ground-truth correction flow maps for the training guidance. However, such labels are expensive, which can only be obtained manually. In this work, we propose a semi-supervised scheme, which can consume unlabeled data in addition to the labeled data for improvements. Specifically, our semi-supervised scheme takes the advantages of the consistency mechanism, with several novel components such as direction and range consistency (DRC) and regression consistency (RC). Furthermore, our network, named as Multi-Scale Swin-Unet (MS-Unet), is built upon the multi-scale swin transformer block (MSTB), which can learn both local-scale and long-range semantic information effectively. In addition, we introduce a highquality unlabeled dataset with rich scenarios for the training. Extensive experiments demonstrate that the proposed method is superior over the state-of-the-art methods and other representative baselines.

show abstract

Semi-Supervised Segmentation of Salt Bodies in Seismic Images using an Ensemble of Convolutional Neural Networks

Cited by 3 publications

References 37 publications

Self-training with Noisy Student improves ImageNet classification

Self-training with Noisy Student improves ImageNet classification

A Benchmark on Tricks for Large-scale Image Retrieval

Semi-Supervised Wide-Angle Portraits Correction by Multi-Scale Transformer

Contact Info

Product

Resources

About