S4L: Self-Supervised Semi-Supervised Learning

Beyer, Lucas; Zhai, Xiaohua; Oliver, Avital; Kolesnikov, Alexander

doi:10.1109/iccv.2019.00156

Cited by 545 publications

(332 citation statements)

References 8 publications

Supporting

Mentioning

325

Contrasting

Order By: Relevance

“…Therefore, the pseudo labels on unlabeled data can be wrong and mislead the classification model. S4L [23] applies selfsupervised learning on unlabeled data. The jigsaw pretext task can improve the performance a little, while rotation de- clines the classification accuracy.…”

Section: Comparison Resultsmentioning

confidence: 99%

Semi-Supervised Learning for Mars Imagery Classification

Wang

Lin

Fan

et al. 2021

2021 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

With the progress of Mars exploration, numerous Mars image data are collected and need to be analyzed. However, because of the imbalance and distortion in Mars data, the performance of existing classification models is unsatisfactory. In this paper, we design a new framework based on semi-supervised contrastive learning for Mars rover image classification. The redundancy of Mars data can disable the effectiveness of contrastive learning. To strip out problematic learning samples, we propose to ignore inner-class pairs on labeled data as well as neglect negative pairs on unlabeled data. Experimental results show that our learning strategies can improve the classification model by a large margin and outperform state-of-theart methods.

show abstract

Section: Comparison Resultsmentioning

confidence: 99%

Semi-Supervised Learning for Mars Imagery Classification

Wang

Lin

Fan

et al. 2021

2021 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

show abstract

“…Semantic cluster deep hashing (SCDH) [12] algorithm introduced a novel classification based semantic cluster unary loss, which bridges the gap between the classification based unary loss and the triplet loss. However, existing deep supervised hashing methods need large amounts of labelled data, which is a severely limit to deploy machine learning systems for new unseen images [34].…”

Section: Related Work a Deep Hashing Methodsmentioning

confidence: 99%

Pseudo Labels and Soft Multi-Part Corresponding Similarity for Unsupervised Deep Hashing

Xie

et al. 2020

IEEE Access

View full text Add to dashboard Cite

In recent years, unsupervised deep hashing methods have achieved great success in large-scale image retrieval. However, these approaches still suffer two major problems in real world applications. On the one hand, due to the lack of effective supervision information, hash codes of different categories are easily judged to be similar. On the other hand, binary semantic similarity matrices can not reflect ranking relationship and the internal structure information of different images. To solve these problems, we propose a novel unsupervised deep hashing method, named Pseudo labels and Soft multi-part Corresponding similarity based Hashing (PSCH), to ensure the heterogeneity of the hash codes. Specifically, we propose a ''pseudo labels'' method that use k-means clustering and a distance threshold to generate the pseudo labels. Further, in order to reflect the hash codes similarity between instances within the same class, we propose a novel soft multi-part corresponding similarity method to learn better hash codes. This method can divide deep feature maps into several groups and compute the attention map for multi-part similarity matrices. In addition, a novel loss function is proposed to support learning with pseudo labels and soft multi-part corresponding similarity for achieving better performance. Comprehensive experiments on CIFAR-10, NUSWIDE, and Flickr demonstrate that our method can generate high-quality hash codes and outperform state-of-the-art unsupervised hashing methods by a large margin.

show abstract

“…There are normally two assumptions: (1) we only care about the performance of the main task and (2) the supervision for the auxiliary tasks is easier to obtain than that of the main task. Previous work has employed various kinds of self-supervised methods as auxiliary tasks for the main supervised task in a semi-supervised setting [30,10,42]. For instance, generative approaches have been explored in [30] and predicting the orientation of image patches is used in [10].…”

Section: Related Workmentioning

confidence: 99%

Hyperspectral Image Super-Resolution with RGB Image Super-Resolution as an Auxiliary Task

Dai²,

Gool

2022

2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

View full text Add to dashboard Cite

This work studies Hyperspectral image (HSI) superresolution (SR). HSI SR is characterized by highdimensional data and a limited amount of training examples. This raises challenges for training deep neural networks that are known to be data hungry. This work addresses this issue with two contributions. First, we observe that HSI SR and RGB image SR are correlated and develop a novel multi-tasking network to train them jointly so that the auxiliary task RGB image SR can provide additional supervision and regulate the network training. Second, we extend the network to a semi-supervised setting so that it can learn from datasets containing only low-resolution HSIs. With these contributions, our method is able to learn hyperspectral image super-resolution from heterogeneous datasets and lifts the requirement for having a large amount of high resolution (HR) HSI training samples. Extensive experiments on three standard datasets show that our method outperforms existing methods significantly and underpin the relevance of our contributions. Our code can be found at https://github.com/kli8996/HSISR.git.

show abstract

S4L: Self-Supervised Semi-Supervised Learning

Cited by 545 publications

References 8 publications

Semi-Supervised Learning for Mars Imagery Classification

Semi-Supervised Learning for Mars Imagery Classification

Pseudo Labels and Soft Multi-Part Corresponding Similarity for Unsupervised Deep Hashing

Hyperspectral Image Super-Resolution with RGB Image Super-Resolution as an Auxiliary Task

Contact Info

Product

Resources

About