Nearest Neighbor Classifier Embedded Network for Active Learning

Wan, Fang; Yuan, Tianning; Fu, Mengying; Ji, Xiangyang; Huang, Qingming; Ye, Qixiang

doi:10.1609/aaai.v35i11.17205

Cited by 12 publications

(3 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…RMQCAL [104] is a novel scalable DAL method, which allows for any number and type of query criteria, eliminates the need for empirical parameters, and makes the tradeoffs between the query criteria self-adaptive. On the other hand, Wan et al [189] propose an embedded network of nearest-neighbor classifiers to enhance the generalization ability of models trained in labeled and unlabeled subspaces in a simple but effective manner. Deng et al [190] focus on combining sample annotation and counterfactual sample construction in the DAL procedure to enhance the model's out-of-distribution generalization.…”

Section: Challenges and Opportunities Of Dalmentioning

confidence: 99%

A Survey on Deep Active Learning: Recent Advances and New Frontiers

Li,

Wang,

Chen

et al. 2024

IEEE Trans. Neural Netw. Learning Syst.

View full text Add to dashboard Cite

Active learning seeks to achieve strong performance with fewer training samples. It does this by iteratively asking an oracle to label newly selected samples in a human-in-the-loop manner. This technique has gained increasing popularity due to its broad applicability, yet its survey papers, especially for deep active learning (DAL), remain scarce. Therefore, we conduct an advanced and comprehensive survey on DAL. We first introduce reviewed paper collection and filtering. Second, we formally define the DAL task and summarize the most influential baselines and widely used datasets. Third, we systematically provide a taxonomy of DAL methods from five perspectives, including annotation types, query strategies, deep model architectures, learning paradigms, and training processes, and objectively analyze their strengths and weaknesses. Then, we comprehensively summarize the main applications of DAL in natural language processing (NLP), computer vision (CV), data mining (DM), and so on. Finally, we discuss challenges and perspectives after a detailed analysis of current studies. This work aims to serve as a useful and quick guide for researchers in overcoming difficulties in DAL. We hope that this survey will spur further progress in this burgeoning field.

show abstract

Section: Challenges and Opportunities Of Dalmentioning

confidence: 99%

A Survey on Deep Active Learning: Recent Advances and New Frontiers

Li,

Wang,

Chen

et al. 2024

IEEE Trans. Neural Netw. Learning Syst.

View full text Add to dashboard Cite

show abstract

“…Another current state-of-the-art work [1] uses k-means++ to achieve diverse acquired samples, along with an acquisition function built on the value of loss gradients relative to model parameters as the value of potential model change. In the work [34] the authors suggest using KNN classifier as the output layer of the network instead of softmax, due to better generalization ability to the unknown space.…”

Section: Related Workmentioning

confidence: 99%

Scalable Batch Acquisition for Deep Bayesian Active Learning

Rubashevskii¹,

Kotova²,

Panov³

2023

Preprint

View full text Add to dashboard Cite

In deep active learning, it is especially important to choose multiple examples to markup at each step to work efficiently, especially on large datasets. At the same time, existing solutions to this problem in the Bayesian setup, such as BatchBALD, have significant limitations in selecting a large number of examples, associated with the exponential complexity of computing mutual information for joint random variables. We, therefore, present the Large BatchBALD algorithm, which gives a well-grounded approximation to the BatchBALD method that aims to achieve comparable quality while being more computationally efficient. We provide a complexity analysis of the algorithm, showing a reduction in computation time, especially for large batches. Furthermore, we present an extensive set of experimental results on image and text data, both on toy datasets and larger ones such as CIFAR-100.

show abstract

“…For example, Batchbald [40] use the method of minimizing conditional entropy as the basis for finding a decision function to greedily select samples that can minimize the entropy of the current model. In order to solve the overconfident prediction of samples out of distribution caused by the model's dependence on classification probability, NN classifier [41] designs a classifier based on the nearest neighbour and support vector to make the model generate high uncertainty for samples far from the existing training data. Different from the above methods, CoreLog [42] gives the measure of uncertainty based on proper scoring rules.…”

Section: Related Workmentioning

confidence: 99%

An active learning method based on result quality evaluation for printed circuit board computed tomography image segmentation

Song,

Qiao,

Yang

et al. 2023

IET Image Processing

View full text Add to dashboard Cite

Element detection is a key step in non‐destructive testing of printed circuit board (PCB) based on computed tomography (CT). In recent years, some image segmentation methods based on deep learning have shown great potential in the element segmentation task of PCB CT images, and greatly improved the efficiency and accuracy. However, since image segmentation is based on pixel‐level classification, the annotation of training data is difficult and costly. Aiming at this problem, the authors proposed a new active learning method based on the integration of relevant information about segmentation tasks and data variance. In this method, the Result Quality Evaluation Module (RQEM) proposed by us is used to generate task‐related information, and an adversarial network is used to generate the difference information between samples and the initial labelled data. Finally, the two parts of information are fused and used as the standard of data selecting. In the PCB CT image element segmentation task, the authors only need to select 12.7% of the whole training set with their proposed method to make Mean Intersection Over Union (MIOU) reach 79.7, which has reached 95% of the optimal performance of 83.7. The in‐depth analysis also verifies the effectiveness and stability of the authors’ method.

show abstract

Nearest Neighbor Classifier Embedded Network for Active Learning

Cited by 12 publications

References 21 publications

A Survey on Deep Active Learning: Recent Advances and New Frontiers

A Survey on Deep Active Learning: Recent Advances and New Frontiers

Scalable Batch Acquisition for Deep Bayesian Active Learning

An active learning method based on result quality evaluation for printed circuit board computed tomography image segmentation

Contact Info

Product

Resources

About