Label Propagation for Deep Semi-Supervised Learning

İşcen, Ahmet; Tolias, Giorgos; Avrithis, Yannis; Chum, Ondřej

doi:10.1109/cvpr.2019.00521

Cited by 563 publications

(501 citation statements)

References 32 publications

Supporting

Mentioning

459

Contrasting

Order By: Relevance

“…The same principle is adopted by Shi et al [29], where the authors further add contrastive loss to the consistency loss. Iscen et al [30] employ a transductive label propagation method that is based on the manifold assumption to make predictions on the entire dataset and use these predictions to generate pseudo-labels for the unlabeled data and train a deep neural network.…”

Section: Deep Semi-supervised Learningmentioning

confidence: 99%

Progressive Cross-Camera Soft-Label Learning for Semi-Supervised Person Re-Identification

Wang

Huo

et al. 2020

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

In this paper, we focus on the semi-supervised person re-identification (Re-ID) case, which only has the intracamera (within-camera) labels but not inter-camera (crosscamera) labels. In real-world applications, these intra-camera labels can be readily captured by tracking algorithms or few manual annotations, when compared with cross-camera labels. In this case, it is very difficult to explore the relationships between cross-camera persons in the training stage due to the lack of cross-camera label information. To deal with this issue, we propose a novel Progressive Cross-camera Soft-label Learning (PCSL) framework for the semi-supervised person Re-ID task, which can generate cross-camera soft-labels and utilize them to optimize the network. Concretely, we calculate an affinity matrix based on person-level features and adapt them to produce the similarities between cross-camera persons (i.e., cross-camera soft-labels). To exploit these soft-labels to train the network, we investigate the weighted cross-entropy loss and the weighted triplet loss from the classification and discrimination perspectives, respectively. Particularly, the proposed framework alternately generates progressive cross-camera soft-labels and gradually improves feature representations in the whole learning course. Extensive experiments on five large-scale benchmark datasets show that PCSL significantly outperforms the state-of-the-art unsupervised methods that employ labeled source domains or the images generated by the GAN-based models. Furthermore, the proposed method even has a competitive performance with respect to deep supervised Re-ID methods.

show abstract

Section: Deep Semi-supervised Learningmentioning

confidence: 99%

Progressive Cross-Camera Soft-Label Learning for Semi-Supervised Person Re-Identification

Wang

Huo

et al. 2020

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

show abstract

“…SSL is a transversal task for different domains including images [6], audio [12], time series [13], and text [14]. Recent approaches in image classification primarily focus on exploiting the consistency in the predictions for the same sample under different perturbations (consistency regularization) [11,15], while other approaches directly generate labels for the unlabeled data to guide the learning process (pseudo-labeling) [16,17]. These two alternatives differ importantly in the mechanism they use to exploit unlabeled samples.…”

Section: Introductionmentioning

confidence: 99%

Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning

Arazo

Ortego

Albert

et al. 2020

2020 International Joint Conference on Neural Networks (IJCNN)

546

327

View full text Add to dashboard Cite

Semi-supervised learning, i.e. jointly learning from labeled and unlabeled samples, is an active research topic due to its key role on relaxing human supervision. In the context of image classification, recent advances to learn from unlabeled samples are mainly focused on consistency regularization methods that encourage invariant predictions for different perturbations of unlabeled samples. We, conversely, propose to learn from unlabeled data by generating soft pseudo-labels using the network predictions. We show that a naive pseudo-labeling overfits to incorrect pseudo-labels due to the so-called confirmation bias and demonstrate that mixup augmentation and setting a minimum number of labeled samples per mini-batch are effective regularization techniques for reducing it. The proposed approach achieves state-of-the-art results in CIFAR-10/100, SVHN, and Mini-ImageNet despite being much simpler than other methods. These results demonstrate that pseudo-labeling alone can outperform consistency regularization methods, while the opposite was supposed in previous work. Source code is available at https://git.io/fjQsC.

show abstract

“…The semi-supervised deep learning model generates three modules to exploit unlabeled data by considering model initialization, diversity augmentation, and pseudo-label editing. Graphbased transduction approach that works through the propagation of few labels, called label propagation, was used in [17] to improve the classification performances and obtain estimated labels. This method consists of two steps.…”

Section: Semi-supervised Learning Defense Algorithmsmentioning

confidence: 99%

On defending against label flipping attacks on malware detection systems

Taheri

Javidan

Shojafar

et al. 2020

Neural Comput & Applic

View full text Add to dashboard Cite

Label manipulation attacks are a subclass of data poisoning attacks in adversarial machine learning used against different applications, such as malware detection. These types of attacks represent a serious threat to detection systems in environments having high noise rate or uncertainty, such as complex networks and Internet of Thing (IoT). Recent work in the literature has suggested using the K-Nearest Neighboring (KNN) algorithm to defend against such attacks. However, such an approach can suffer from low to wrong detection accuracy. In this paper, we design an architecture to tackle the Android malware detection problem in IoT systems. We develop an attack mechanism based on Silhouette clustering method, modified for mobile Android platforms. We proposed two Convolutional Neural Network (CNN)-type deep learning algorithms against this Silhouette Clustering-based Label Flipping Attack (SCLFA). We show the effectiveness of these two defense algorithms -Label-based Semi-supervised Defense (LSD) and clustering-based Semi-supervised Defense (CSD) -in correcting labels being attacked. We evaluate the performance of the proposed algorithms by varying the various machine learning parameters on three Android datasets: Drebin, Contagio, and Genome and three types of features: API, intent, and permission. Our evaluation shows that using random forest feature selection and varying ratios of features can result in an improvement of up to 19% accuracy when compared with the state-of-the-art method in the literature.

show abstract

Label Propagation for Deep Semi-Supervised Learning

Cited by 563 publications

References 32 publications

Progressive Cross-Camera Soft-Label Learning for Semi-Supervised Person Re-Identification

Progressive Cross-Camera Soft-Label Learning for Semi-Supervised Person Re-Identification

Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning

On defending against label flipping attacks on malware detection systems

Contact Info

Product

Resources

About