Self-augmentation: Generalizing deep networks to unseen classes for few-shot learning

Seo, Jeong-Hyun; Jung, Hong-Gyu; Lee, Seong Whan

doi:10.1016/j.neunet.2021.02.007

Cited by 34 publications

(8 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Unfortunately, these algorithms traditionally rely on large datasets. Recent advances in few-shot learning and data augmentation methods allow for deep learning approaches using small datasets—an excellent fit for the relative paucity of validated ototoxins in our training dataset ( 163 – 165 ). Another option is to use transcriptomic data for model fitting, either in lieu of or in addition to molecular fingerprints.…”

Section: Models For Ototoxicity Studiesmentioning

confidence: 99%

Detecting Novel Ototoxins and Potentiation of Ototoxicity by Disease Settings

Coffin

Boney²,

Hill

et al. 2021

Front. Neurol.

View full text Add to dashboard Cite

Over 100 drugs and chemicals are associated with permanent hearing loss, tinnitus, and vestibular deficits, collectively known as ototoxicity. The ototoxic potential of drugs is rarely assessed in pre-clinical drug development or during clinical trials, so this debilitating side-effect is often discovered as patients begin to report hearing loss. Furthermore, drug-induced ototoxicity in adults, and particularly in elderly patients, may go unrecognized due to hearing loss from a variety of etiologies because of a lack of baseline assessments immediately prior to novel therapeutic treatment. During the current pandemic, there is an intense effort to identify new drugs or repurpose FDA-approved drugs to treat COVID-19. Several potential COVID-19 therapeutics are known ototoxins, including chloroquine (CQ) and lopinavir-ritonavir, demonstrating the necessity to identify ototoxic potential in existing and novel medicines. Furthermore, several factors are emerging as potentiators of ototoxicity, such as inflammation (a hallmark of COVID-19), genetic polymorphisms, and ototoxic synergy with co-therapeutics, increasing the necessity to evaluate a drug's potential to induce ototoxicity under varying conditions. Here, we review the potential of COVID-19 therapies to induce ototoxicity and factors that may compound their ototoxic effects. We then discuss two models for rapidly detecting the potential for ototoxicity: mammalian auditory cell lines and the larval zebrafish lateral line. These models offer considerable value for pre-clinical drug development, including development of COVID-19 therapies. Finally, we show the validity of in silico screening for ototoxic potential using a computational model that compares structural similarity of compounds of interest with a database of known ototoxins and non-ototoxins. Preclinical screening at in silico, in vitro, and in vivo levels can provide an earlier indication of the potential for ototoxicity and identify the subset of candidate therapeutics for treating COVID-19 that need to be monitored for ototoxicity as for other widely-used clinical therapeutics, like aminoglycosides and cisplatin.

show abstract

Section: Models For Ototoxicity Studiesmentioning

confidence: 99%

Detecting Novel Ototoxins and Potentiation of Ototoxicity by Disease Settings

Coffin

Boney²,

Hill

et al. 2021

Front. Neurol.

View full text Add to dashboard Cite

show abstract

“…NeuNet since neural network has the advantage of self-learning [13]. This work focused on how to set the optimization goals in NeuNet .…”

Section: Dynamic Aggregationmentioning

confidence: 99%

Federated Learning with Random Communication and Dynamic Aggregation

Huang¹,

Lu²,

Luo³

et al. 2021

Machine Learning Techniques and Data Science

View full text Add to dashboard Cite

Federated Learning (FL) is a setting that allows clients to train a joint global model collaboratively while keeping data locally. Due to FL has advantages of data confidential and distributed computing, interest in this area has increased. In this paper, we designed a new FL algorithm named FedRAD. Random communication and dynamic aggregation methods are proposed for FedRAD. Random communication method enables FL system use the combination of fixed communication interval and constrained variable intervals in a single task. Dynamic aggregation method reforms aggregation weights and makes weights update automately. Both methods aim to improve model performance. We evaluated two proposed methods respectively, and compared FedRAD with three algorithms on three hyperparameters. Results at CIFAR-10 demonstrate that each method has good performance, and FedRAD can achieve higher classification accuracy than state-of-the-art FL algorithms.

show abstract

“…We adapted a couple of augmentation techniques such as CutMix [70], where image patches are cut and pasted among training images and the ground truth labels are also mixed proportionally within the area of the patches. Mixup [50], a technique that generates convex combinations of pairs of examples and their labels, which proved to be effective for support and query augmentation strategies. As well as Self-Mix [71] in which an image is substituted into other regions in the same image.…”

Section: Data Augmentation Strategymentioning

confidence: 99%

“…We investigated three test cases that check the training performance when data is sampled from the support, query and task data, respectively. Our approach is similar to techniques adapted by [41,30,50] that examine the impact of augmentation on a diverse set of data combinations.…”

Section: Augmentation Performancementioning

confidence: 99%

Ortho-Shot: Low Displacement Rank Regularization with Data Augmentation for Few-Shot Learning

Osahor¹,

Nasrabadi²

2021

Preprint

View full text Add to dashboard Cite

In few-shot classification, the primary goal is to learn representations from a few samples that generalize well for novel classes. In this paper, we propose an efficient low displacement rank (LDR) regularization strategy termed Ortho-Shot; a technique that imposes orthogonal regularization on the convolutional layers of a few-shot classifier, which is based on the doubly-block toeplitz (DBT) matrix structure. The regularized convolutional layers of the few-shot classifier enhances model generalization and intra-class feature embeddings that are crucial for few-shot learning. Overfitting is a typical issue for few-shot models, the lack of data diversity inhibits proper model inference which weakens the classification accuracy of few-shot learners to novel classes. In this regard, we broke down the pipeline of the few-shot classifier and established that the support, query and task data augmentation collectively alleviates overfitting in networks. With compelling results, we demonstrated that combining a DBT-based low-rank orthogonal regularizer with data augmentation strategies, significantly boosts the performance of a few-shot classifier. We perform our experiments on the miniImagenet, CIFAR-FS and Stanford datasets with performance values of about 5% when compared to state-of-the-art.

show abstract

Self-augmentation: Generalizing deep networks to unseen classes for few-shot learning

Cited by 34 publications

References 28 publications

Detecting Novel Ototoxins and Potentiation of Ototoxicity by Disease Settings

Detecting Novel Ototoxins and Potentiation of Ototoxicity by Disease Settings

Federated Learning with Random Communication and Dynamic Aggregation

Ortho-Shot: Low Displacement Rank Regularization with Data Augmentation for Few-Shot Learning

Contact Info

Product

Resources

About