Mutual exclusivity loss for semi-supervised deep learning

Sajjadi, Mehdi S. M.; Javanmardi, Mehran; Taşdizen, Tolga

doi:10.1109/icip.2016.7532690

Cited by 149 publications

(180 citation statements)

References 19 publications

Supporting

Mentioning

133

Contrasting

Unclassified

Order By: Relevance

“…It is reported to be an essential technique required by DLAs to achieve good performance. [34] However, we did not apply data augmentation because it has a high potential to distort shape, margin, echogenicity, and calcification, which are essential for differentiating benignity and malignancy.…”

Section: Discussionmentioning

confidence: 99%

Ultrasound image analysis using deep learning algorithm for the diagnosis of thyroid nodules

et al. 2019

View full text Add to dashboard Cite

show abstract

Section: Discussionmentioning

confidence: 99%

Ultrasound image analysis using deep learning algorithm for the diagnosis of thyroid nodules

et al. 2019

View full text Add to dashboard Cite

show abstract

“…coming from two similar images, or made by two networks with related parameters, are encouraged to have similar network outputs. Sajjadi et al [34] is the first, to our knowledge, to use a consistency loss between the outputs of a network on random perturbations of the same image. Laine and Aila [23] rather apply consistency between the output of the current network and the temporal average of outputs during training.…”

Section: Related Workmentioning

confidence: 99%

Label Propagation for Deep Semi-Supervised Learning

İşcen

Tolias

Avrithis

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

559

459

View full text Add to dashboard Cite

Semi-supervised learning is becoming increasingly important because it can combine data carefully labeled by humans with abundant unlabeled data to train deep neural networks. Classic methods on semi-supervised learning that have focused on transductive learning have not been fully exploited in the inductive framework followed by modern deep learning. The same holds for the manifold assumption-that similar examples should get the same prediction. In this work, we 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. At the core of the transductive method lies a nearest neighbor graph of the dataset that we create based on the embeddings of the same network. Therefore our learning process iterates between these two steps. We improve performance on several datasets especially in the few labels regime and show that our work is complementary to current state of the art.

show abstract

“…For example, Sajjadi et al [24] assume that every training image, labeled or not, belongs to a single category, a natural requirement on the classifier is to make a confident prediction on the training set by minimizing the entropy of the network output. Besides, [61], [62], [27], [63] focus on consistency loss, where two related cases, e.g., coming from two similar images, or made by two networks with related parameters, are encouraged to have similar network outputs.…”

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

Mutual exclusivity loss for semi-supervised deep learning

Cited by 149 publications

References 19 publications

Ultrasound image analysis using deep learning algorithm for the diagnosis of thyroid nodules

Ultrasound image analysis using deep learning algorithm for the diagnosis of thyroid nodules

Label Propagation for Deep Semi-Supervised Learning

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

Contact Info

Product

Resources

About